diff --git a/hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/__init__.py b/hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/__init__.py deleted file mode 100644 index 8b137891791fe96927ad78e64b0aad7bded08bdc..0000000000000000000000000000000000000000 --- a/hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/__init__.py +++ /dev/null @@ -1 +0,0 @@ - diff --git a/modules/image/Image_gan/style_transfer/U2Net_Portrait/u2net.py b/modules/image/Image_gan/style_transfer/U2Net_Portrait/u2net.py deleted file mode 100644 index c73815cf490879d0bdeecaba050d7342278cd3de..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/U2Net_Portrait/u2net.py +++ /dev/null @@ -1,527 +0,0 @@ -import paddle -import paddle.nn as nn -import paddle.nn.functional as F - -__all__ = ['U2NETP', 'U2NET'] - -class REBNCONV(nn.Layer): - def __init__(self,in_ch=3,out_ch=3,dirate=1): - super(REBNCONV,self).__init__() - - self.conv_s1 = nn.Conv2D(in_ch,out_ch,3,padding=1*dirate,dilation=1*dirate) - self.bn_s1 = nn.BatchNorm2D(out_ch) - self.relu_s1 = nn.ReLU() - - def forward(self,x): - - hx = x - xout = self.relu_s1(self.bn_s1(self.conv_s1(hx))) - - return xout - -## upsample tensor 'src' to have the same spatial size with tensor 'tar' -def _upsample_like(src,tar): - - src = F.upsample(src,size=tar.shape[2:],mode='bilinear') - - return src - - -### RSU-7 ### -class RSU7(nn.Layer):#UNet07DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU7,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool4 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool5 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv6 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv7 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv6d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv5d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - hx = self.pool4(hx4) - - hx5 = self.rebnconv5(hx) - hx = self.pool5(hx5) - - hx6 = self.rebnconv6(hx) - - hx7 = self.rebnconv7(hx6) - - hx6d = self.rebnconv6d(paddle.concat((hx7,hx6),1)) - hx6dup = _upsample_like(hx6d,hx5) - - hx5d = self.rebnconv5d(paddle.concat((hx6dup,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-6 ### -class RSU6(nn.Layer):#UNet06DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU6,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool4 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv6 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv5d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - hx = self.pool4(hx4) - - hx5 = self.rebnconv5(hx) - - hx6 = self.rebnconv6(hx5) - - - hx5d = self.rebnconv5d(paddle.concat((hx6,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-5 ### -class RSU5(nn.Layer):#UNet05DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU5,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - - hx5 = self.rebnconv5(hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-4 ### -class RSU4(nn.Layer):#UNet04DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU4,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - - hx4 = self.rebnconv4(hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-4F ### -class RSU4F(nn.Layer):#UNet04FRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU4F,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=2) - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=4) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=8) - - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=4) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=2) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx2 = self.rebnconv2(hx1) - hx3 = self.rebnconv3(hx2) - - hx4 = self.rebnconv4(hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4,hx3),1)) - hx2d = self.rebnconv2d(paddle.concat((hx3d,hx2),1)) - hx1d = self.rebnconv1d(paddle.concat((hx2d,hx1),1)) - - return hx1d + hxin - - -##### U^2-Net #### -class U2NET(nn.Layer): - - def __init__(self,in_ch=3,out_ch=1): - super(U2NET,self).__init__() - - self.stage1 = RSU7(in_ch,32,64) - self.pool12 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage2 = RSU6(64,32,128) - self.pool23 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage3 = RSU5(128,64,256) - self.pool34 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage4 = RSU4(256,128,512) - self.pool45 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage5 = RSU4F(512,256,512) - self.pool56 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage6 = RSU4F(512,256,512) - - # decoder - self.stage5d = RSU4F(1024,256,512) - self.stage4d = RSU4(1024,128,256) - self.stage3d = RSU5(512,64,128) - self.stage2d = RSU6(256,32,64) - self.stage1d = RSU7(128,16,64) - - self.side1 = nn.Conv2D(64,out_ch,3,padding=1) - self.side2 = nn.Conv2D(64,out_ch,3,padding=1) - self.side3 = nn.Conv2D(128,out_ch,3,padding=1) - self.side4 = nn.Conv2D(256,out_ch,3,padding=1) - self.side5 = nn.Conv2D(512,out_ch,3,padding=1) - self.side6 = nn.Conv2D(512,out_ch,3,padding=1) - - self.outconv = nn.Conv2D(6,out_ch,1) - - def forward(self,x): - - hx = x - - #stage 1 - hx1 = self.stage1(hx) - hx = self.pool12(hx1) - - #stage 2 - hx2 = self.stage2(hx) - hx = self.pool23(hx2) - - #stage 3 - hx3 = self.stage3(hx) - hx = self.pool34(hx3) - - #stage 4 - hx4 = self.stage4(hx) - hx = self.pool45(hx4) - - #stage 5 - hx5 = self.stage5(hx) - hx = self.pool56(hx5) - - #stage 6 - hx6 = self.stage6(hx) - hx6up = _upsample_like(hx6,hx5) - - #-------------------- decoder -------------------- - hx5d = self.stage5d(paddle.concat((hx6up,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.stage4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.stage3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.stage2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.stage1d(paddle.concat((hx2dup,hx1),1)) - - - #side output - d1 = self.side1(hx1d) - - d2 = self.side2(hx2d) - d2 = _upsample_like(d2,d1) - - d3 = self.side3(hx3d) - d3 = _upsample_like(d3,d1) - - d4 = self.side4(hx4d) - d4 = _upsample_like(d4,d1) - - d5 = self.side5(hx5d) - d5 = _upsample_like(d5,d1) - - d6 = self.side6(hx6) - d6 = _upsample_like(d6,d1) - - d0 = self.outconv(paddle.concat((d1,d2,d3,d4,d5,d6),1)) - - return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) - -### U^2-Net small ### -class U2NETP(nn.Layer): - - def __init__(self,in_ch=3,out_ch=1): - super(U2NETP,self).__init__() - - self.stage1 = RSU7(in_ch,16,64) - self.pool12 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage2 = RSU6(64,16,64) - self.pool23 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage3 = RSU5(64,16,64) - self.pool34 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage4 = RSU4(64,16,64) - self.pool45 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage5 = RSU4F(64,16,64) - self.pool56 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage6 = RSU4F(64,16,64) - - # decoder - self.stage5d = RSU4F(128,16,64) - self.stage4d = RSU4(128,16,64) - self.stage3d = RSU5(128,16,64) - self.stage2d = RSU6(128,16,64) - self.stage1d = RSU7(128,16,64) - - self.side1 = nn.Conv2D(64,out_ch,3,padding=1) - self.side2 = nn.Conv2D(64,out_ch,3,padding=1) - self.side3 = nn.Conv2D(64,out_ch,3,padding=1) - self.side4 = nn.Conv2D(64,out_ch,3,padding=1) - self.side5 = nn.Conv2D(64,out_ch,3,padding=1) - self.side6 = nn.Conv2D(64,out_ch,3,padding=1) - - self.outconv = nn.Conv2D(6,out_ch,1) - - def forward(self,x): - - hx = x - - #stage 1 - hx1 = self.stage1(hx) - hx = self.pool12(hx1) - - #stage 2 - hx2 = self.stage2(hx) - hx = self.pool23(hx2) - - #stage 3 - hx3 = self.stage3(hx) - hx = self.pool34(hx3) - - #stage 4 - hx4 = self.stage4(hx) - hx = self.pool45(hx4) - - #stage 5 - hx5 = self.stage5(hx) - hx = self.pool56(hx5) - - #stage 6 - hx6 = self.stage6(hx) - hx6up = _upsample_like(hx6,hx5) - - #decoder - hx5d = self.stage5d(paddle.concat((hx6up,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.stage4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.stage3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.stage2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.stage1d(paddle.concat((hx2dup,hx1),1)) - - - #side output - d1 = self.side1(hx1d) - - d2 = self.side2(hx2d) - d2 = _upsample_like(d2,d1) - - d3 = self.side3(hx3d) - d3 = _upsample_like(d3,d1) - - d4 = self.side4(hx4d) - d4 = _upsample_like(d4,d1) - - d5 = self.side5(hx5d) - d5 = _upsample_like(d5,d1) - - d6 = self.side6(hx6) - d6 = _upsample_like(d6,d1) - - d0 = self.outconv(paddle.concat((d1,d2,d3,d4,d5,d6),1)) - - return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/model.py b/modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/model.py deleted file mode 100644 index 3adadc9232afaaafe31b3520ad54db406bc42229..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/model.py b/modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/model.py deleted file mode 100644 index 3adadc9232afaaafe31b3520ad54db406bc42229..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/model.py b/modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/model.py deleted file mode 100644 index 3adadc9232afaaafe31b3520ad54db406bc42229..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/model.py b/modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/model.py deleted file mode 100644 index 3adadc9232afaaafe31b3520ad54db406bc42229..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/model.py b/modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/model.py deleted file mode 100644 index 3adadc9232afaaafe31b3520ad54db406bc42229..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/model.py b/modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/model.py deleted file mode 100644 index 3adadc9232afaaafe31b3520ad54db406bc42229..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/model.py b/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/model.py deleted file mode 100644 index 3adadc9232afaaafe31b3520ad54db406bc42229..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/model.py b/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/model.py deleted file mode 100644 index 3adadc9232afaaafe31b3520ad54db406bc42229..0000000000000000000000000000000000000000 --- a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/keypoint_detection/hand_pose_localization/model.py b/modules/image/keypoint_detection/hand_pose_localization/model.py deleted file mode 100644 index 81d177ea8dc02f6775fc9789ec7eb68eda485b4c..0000000000000000000000000000000000000000 --- a/modules/image/keypoint_detection/hand_pose_localization/model.py +++ /dev/null @@ -1,73 +0,0 @@ -import os -import numpy as np - -from paddle.inference import create_predictor, Config - -__all__ = ['Model'] - -class Model(): - # 初始化函数 - def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): - # 加载模型预测器 - self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) - - # 获取模型的输入输出 - self.input_names = self.predictor.get_input_names() - self.output_names = self.predictor.get_output_names() - self.input_handle = self.predictor.get_input_handle(self.input_names[0]) - self.output_handle = self.predictor.get_output_handle(self.output_names[0]) - - # 模型加载函数 - def load_model(self, modelpath, use_gpu, use_mkldnn, combined): - # 对运行位置进行配置 - if use_gpu: - try: - int(os.environ.get('CUDA_VISIBLE_DEVICES')) - except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') - use_gpu = False - - # 加载模型参数 - if combined: - model = os.path.join(modelpath, "__model__") - params = os.path.join(modelpath, "__params__") - config = Config(model, params) - else: - config = Config(modelpath) - - # 设置参数 - if use_gpu: - config.enable_use_gpu(100, 0) - else: - config.disable_gpu() - if use_mkldnn: - config.enable_mkldnn() - config.disable_glog_info() - config.switch_ir_optim(True) - config.enable_memory_optim() - config.switch_use_feed_fetch_ops(False) - config.switch_specify_input_names(True) - - # 通过参数加载模型预测器 - predictor = create_predictor(config) - - # 返回预测器 - return predictor - - # 模型预测函数 - def predict(self, input_datas): - outputs = [] - - # 遍历输入数据进行预测 - for input_data in input_datas: - inputs = input_data.copy() - self.input_handle.copy_from_cpu(inputs) - self.predictor.run() - output = self.output_handle.copy_to_cpu() - outputs.append(output) - - # 预测结果合并 - outputs = np.concatenate(outputs, 0) - - # 返回预测结果 - return outputs \ No newline at end of file diff --git a/modules/image/semantic_segmentation/U2Net/u2net.py b/modules/image/semantic_segmentation/U2Net/u2net.py deleted file mode 100644 index c73815cf490879d0bdeecaba050d7342278cd3de..0000000000000000000000000000000000000000 --- a/modules/image/semantic_segmentation/U2Net/u2net.py +++ /dev/null @@ -1,527 +0,0 @@ -import paddle -import paddle.nn as nn -import paddle.nn.functional as F - -__all__ = ['U2NETP', 'U2NET'] - -class REBNCONV(nn.Layer): - def __init__(self,in_ch=3,out_ch=3,dirate=1): - super(REBNCONV,self).__init__() - - self.conv_s1 = nn.Conv2D(in_ch,out_ch,3,padding=1*dirate,dilation=1*dirate) - self.bn_s1 = nn.BatchNorm2D(out_ch) - self.relu_s1 = nn.ReLU() - - def forward(self,x): - - hx = x - xout = self.relu_s1(self.bn_s1(self.conv_s1(hx))) - - return xout - -## upsample tensor 'src' to have the same spatial size with tensor 'tar' -def _upsample_like(src,tar): - - src = F.upsample(src,size=tar.shape[2:],mode='bilinear') - - return src - - -### RSU-7 ### -class RSU7(nn.Layer):#UNet07DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU7,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool4 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool5 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv6 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv7 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv6d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv5d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - hx = self.pool4(hx4) - - hx5 = self.rebnconv5(hx) - hx = self.pool5(hx5) - - hx6 = self.rebnconv6(hx) - - hx7 = self.rebnconv7(hx6) - - hx6d = self.rebnconv6d(paddle.concat((hx7,hx6),1)) - hx6dup = _upsample_like(hx6d,hx5) - - hx5d = self.rebnconv5d(paddle.concat((hx6dup,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-6 ### -class RSU6(nn.Layer):#UNet06DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU6,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool4 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv6 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv5d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - hx = self.pool4(hx4) - - hx5 = self.rebnconv5(hx) - - hx6 = self.rebnconv6(hx5) - - - hx5d = self.rebnconv5d(paddle.concat((hx6,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-5 ### -class RSU5(nn.Layer):#UNet05DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU5,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - - hx5 = self.rebnconv5(hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-4 ### -class RSU4(nn.Layer):#UNet04DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU4,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - - hx4 = self.rebnconv4(hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-4F ### -class RSU4F(nn.Layer):#UNet04FRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU4F,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=2) - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=4) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=8) - - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=4) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=2) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx2 = self.rebnconv2(hx1) - hx3 = self.rebnconv3(hx2) - - hx4 = self.rebnconv4(hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4,hx3),1)) - hx2d = self.rebnconv2d(paddle.concat((hx3d,hx2),1)) - hx1d = self.rebnconv1d(paddle.concat((hx2d,hx1),1)) - - return hx1d + hxin - - -##### U^2-Net #### -class U2NET(nn.Layer): - - def __init__(self,in_ch=3,out_ch=1): - super(U2NET,self).__init__() - - self.stage1 = RSU7(in_ch,32,64) - self.pool12 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage2 = RSU6(64,32,128) - self.pool23 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage3 = RSU5(128,64,256) - self.pool34 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage4 = RSU4(256,128,512) - self.pool45 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage5 = RSU4F(512,256,512) - self.pool56 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage6 = RSU4F(512,256,512) - - # decoder - self.stage5d = RSU4F(1024,256,512) - self.stage4d = RSU4(1024,128,256) - self.stage3d = RSU5(512,64,128) - self.stage2d = RSU6(256,32,64) - self.stage1d = RSU7(128,16,64) - - self.side1 = nn.Conv2D(64,out_ch,3,padding=1) - self.side2 = nn.Conv2D(64,out_ch,3,padding=1) - self.side3 = nn.Conv2D(128,out_ch,3,padding=1) - self.side4 = nn.Conv2D(256,out_ch,3,padding=1) - self.side5 = nn.Conv2D(512,out_ch,3,padding=1) - self.side6 = nn.Conv2D(512,out_ch,3,padding=1) - - self.outconv = nn.Conv2D(6,out_ch,1) - - def forward(self,x): - - hx = x - - #stage 1 - hx1 = self.stage1(hx) - hx = self.pool12(hx1) - - #stage 2 - hx2 = self.stage2(hx) - hx = self.pool23(hx2) - - #stage 3 - hx3 = self.stage3(hx) - hx = self.pool34(hx3) - - #stage 4 - hx4 = self.stage4(hx) - hx = self.pool45(hx4) - - #stage 5 - hx5 = self.stage5(hx) - hx = self.pool56(hx5) - - #stage 6 - hx6 = self.stage6(hx) - hx6up = _upsample_like(hx6,hx5) - - #-------------------- decoder -------------------- - hx5d = self.stage5d(paddle.concat((hx6up,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.stage4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.stage3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.stage2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.stage1d(paddle.concat((hx2dup,hx1),1)) - - - #side output - d1 = self.side1(hx1d) - - d2 = self.side2(hx2d) - d2 = _upsample_like(d2,d1) - - d3 = self.side3(hx3d) - d3 = _upsample_like(d3,d1) - - d4 = self.side4(hx4d) - d4 = _upsample_like(d4,d1) - - d5 = self.side5(hx5d) - d5 = _upsample_like(d5,d1) - - d6 = self.side6(hx6) - d6 = _upsample_like(d6,d1) - - d0 = self.outconv(paddle.concat((d1,d2,d3,d4,d5,d6),1)) - - return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) - -### U^2-Net small ### -class U2NETP(nn.Layer): - - def __init__(self,in_ch=3,out_ch=1): - super(U2NETP,self).__init__() - - self.stage1 = RSU7(in_ch,16,64) - self.pool12 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage2 = RSU6(64,16,64) - self.pool23 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage3 = RSU5(64,16,64) - self.pool34 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage4 = RSU4(64,16,64) - self.pool45 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage5 = RSU4F(64,16,64) - self.pool56 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage6 = RSU4F(64,16,64) - - # decoder - self.stage5d = RSU4F(128,16,64) - self.stage4d = RSU4(128,16,64) - self.stage3d = RSU5(128,16,64) - self.stage2d = RSU6(128,16,64) - self.stage1d = RSU7(128,16,64) - - self.side1 = nn.Conv2D(64,out_ch,3,padding=1) - self.side2 = nn.Conv2D(64,out_ch,3,padding=1) - self.side3 = nn.Conv2D(64,out_ch,3,padding=1) - self.side4 = nn.Conv2D(64,out_ch,3,padding=1) - self.side5 = nn.Conv2D(64,out_ch,3,padding=1) - self.side6 = nn.Conv2D(64,out_ch,3,padding=1) - - self.outconv = nn.Conv2D(6,out_ch,1) - - def forward(self,x): - - hx = x - - #stage 1 - hx1 = self.stage1(hx) - hx = self.pool12(hx1) - - #stage 2 - hx2 = self.stage2(hx) - hx = self.pool23(hx2) - - #stage 3 - hx3 = self.stage3(hx) - hx = self.pool34(hx3) - - #stage 4 - hx4 = self.stage4(hx) - hx = self.pool45(hx4) - - #stage 5 - hx5 = self.stage5(hx) - hx = self.pool56(hx5) - - #stage 6 - hx6 = self.stage6(hx) - hx6up = _upsample_like(hx6,hx5) - - #decoder - hx5d = self.stage5d(paddle.concat((hx6up,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.stage4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.stage3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.stage2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.stage1d(paddle.concat((hx2dup,hx1),1)) - - - #side output - d1 = self.side1(hx1d) - - d2 = self.side2(hx2d) - d2 = _upsample_like(d2,d1) - - d3 = self.side3(hx3d) - d3 = _upsample_like(d3,d1) - - d4 = self.side4(hx4d) - d4 = _upsample_like(d4,d1) - - d5 = self.side5(hx5d) - d5 = _upsample_like(d5,d1) - - d6 = self.side6(hx6) - d6 = _upsample_like(d6,d1) - - d0 = self.outconv(paddle.concat((d1,d2,d3,d4,d5,d6),1)) - - return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) diff --git a/modules/image/semantic_segmentation/U2Netp/u2net.py b/modules/image/semantic_segmentation/U2Netp/u2net.py deleted file mode 100644 index c73815cf490879d0bdeecaba050d7342278cd3de..0000000000000000000000000000000000000000 --- a/modules/image/semantic_segmentation/U2Netp/u2net.py +++ /dev/null @@ -1,527 +0,0 @@ -import paddle -import paddle.nn as nn -import paddle.nn.functional as F - -__all__ = ['U2NETP', 'U2NET'] - -class REBNCONV(nn.Layer): - def __init__(self,in_ch=3,out_ch=3,dirate=1): - super(REBNCONV,self).__init__() - - self.conv_s1 = nn.Conv2D(in_ch,out_ch,3,padding=1*dirate,dilation=1*dirate) - self.bn_s1 = nn.BatchNorm2D(out_ch) - self.relu_s1 = nn.ReLU() - - def forward(self,x): - - hx = x - xout = self.relu_s1(self.bn_s1(self.conv_s1(hx))) - - return xout - -## upsample tensor 'src' to have the same spatial size with tensor 'tar' -def _upsample_like(src,tar): - - src = F.upsample(src,size=tar.shape[2:],mode='bilinear') - - return src - - -### RSU-7 ### -class RSU7(nn.Layer):#UNet07DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU7,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool4 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool5 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv6 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv7 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv6d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv5d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - hx = self.pool4(hx4) - - hx5 = self.rebnconv5(hx) - hx = self.pool5(hx5) - - hx6 = self.rebnconv6(hx) - - hx7 = self.rebnconv7(hx6) - - hx6d = self.rebnconv6d(paddle.concat((hx7,hx6),1)) - hx6dup = _upsample_like(hx6d,hx5) - - hx5d = self.rebnconv5d(paddle.concat((hx6dup,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-6 ### -class RSU6(nn.Layer):#UNet06DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU6,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool4 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv6 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv5d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - hx = self.pool4(hx4) - - hx5 = self.rebnconv5(hx) - - hx6 = self.rebnconv6(hx5) - - - hx5d = self.rebnconv5d(paddle.concat((hx6,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-5 ### -class RSU5(nn.Layer):#UNet05DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU5,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool3 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv5 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv4d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - hx = self.pool3(hx3) - - hx4 = self.rebnconv4(hx) - - hx5 = self.rebnconv5(hx4) - - hx4d = self.rebnconv4d(paddle.concat((hx5,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-4 ### -class RSU4(nn.Layer):#UNet04DRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU4,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.pool1 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=1) - self.pool2 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=1) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=2) - - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=1) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx = self.pool1(hx1) - - hx2 = self.rebnconv2(hx) - hx = self.pool2(hx2) - - hx3 = self.rebnconv3(hx) - - hx4 = self.rebnconv4(hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.rebnconv2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.rebnconv1d(paddle.concat((hx2dup,hx1),1)) - - return hx1d + hxin - -### RSU-4F ### -class RSU4F(nn.Layer):#UNet04FRES(nn.Layer): - - def __init__(self, in_ch=3, mid_ch=12, out_ch=3): - super(RSU4F,self).__init__() - - self.rebnconvin = REBNCONV(in_ch,out_ch,dirate=1) - - self.rebnconv1 = REBNCONV(out_ch,mid_ch,dirate=1) - self.rebnconv2 = REBNCONV(mid_ch,mid_ch,dirate=2) - self.rebnconv3 = REBNCONV(mid_ch,mid_ch,dirate=4) - - self.rebnconv4 = REBNCONV(mid_ch,mid_ch,dirate=8) - - self.rebnconv3d = REBNCONV(mid_ch*2,mid_ch,dirate=4) - self.rebnconv2d = REBNCONV(mid_ch*2,mid_ch,dirate=2) - self.rebnconv1d = REBNCONV(mid_ch*2,out_ch,dirate=1) - - def forward(self,x): - - hx = x - - hxin = self.rebnconvin(hx) - - hx1 = self.rebnconv1(hxin) - hx2 = self.rebnconv2(hx1) - hx3 = self.rebnconv3(hx2) - - hx4 = self.rebnconv4(hx3) - - hx3d = self.rebnconv3d(paddle.concat((hx4,hx3),1)) - hx2d = self.rebnconv2d(paddle.concat((hx3d,hx2),1)) - hx1d = self.rebnconv1d(paddle.concat((hx2d,hx1),1)) - - return hx1d + hxin - - -##### U^2-Net #### -class U2NET(nn.Layer): - - def __init__(self,in_ch=3,out_ch=1): - super(U2NET,self).__init__() - - self.stage1 = RSU7(in_ch,32,64) - self.pool12 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage2 = RSU6(64,32,128) - self.pool23 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage3 = RSU5(128,64,256) - self.pool34 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage4 = RSU4(256,128,512) - self.pool45 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage5 = RSU4F(512,256,512) - self.pool56 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage6 = RSU4F(512,256,512) - - # decoder - self.stage5d = RSU4F(1024,256,512) - self.stage4d = RSU4(1024,128,256) - self.stage3d = RSU5(512,64,128) - self.stage2d = RSU6(256,32,64) - self.stage1d = RSU7(128,16,64) - - self.side1 = nn.Conv2D(64,out_ch,3,padding=1) - self.side2 = nn.Conv2D(64,out_ch,3,padding=1) - self.side3 = nn.Conv2D(128,out_ch,3,padding=1) - self.side4 = nn.Conv2D(256,out_ch,3,padding=1) - self.side5 = nn.Conv2D(512,out_ch,3,padding=1) - self.side6 = nn.Conv2D(512,out_ch,3,padding=1) - - self.outconv = nn.Conv2D(6,out_ch,1) - - def forward(self,x): - - hx = x - - #stage 1 - hx1 = self.stage1(hx) - hx = self.pool12(hx1) - - #stage 2 - hx2 = self.stage2(hx) - hx = self.pool23(hx2) - - #stage 3 - hx3 = self.stage3(hx) - hx = self.pool34(hx3) - - #stage 4 - hx4 = self.stage4(hx) - hx = self.pool45(hx4) - - #stage 5 - hx5 = self.stage5(hx) - hx = self.pool56(hx5) - - #stage 6 - hx6 = self.stage6(hx) - hx6up = _upsample_like(hx6,hx5) - - #-------------------- decoder -------------------- - hx5d = self.stage5d(paddle.concat((hx6up,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.stage4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.stage3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.stage2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.stage1d(paddle.concat((hx2dup,hx1),1)) - - - #side output - d1 = self.side1(hx1d) - - d2 = self.side2(hx2d) - d2 = _upsample_like(d2,d1) - - d3 = self.side3(hx3d) - d3 = _upsample_like(d3,d1) - - d4 = self.side4(hx4d) - d4 = _upsample_like(d4,d1) - - d5 = self.side5(hx5d) - d5 = _upsample_like(d5,d1) - - d6 = self.side6(hx6) - d6 = _upsample_like(d6,d1) - - d0 = self.outconv(paddle.concat((d1,d2,d3,d4,d5,d6),1)) - - return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) - -### U^2-Net small ### -class U2NETP(nn.Layer): - - def __init__(self,in_ch=3,out_ch=1): - super(U2NETP,self).__init__() - - self.stage1 = RSU7(in_ch,16,64) - self.pool12 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage2 = RSU6(64,16,64) - self.pool23 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage3 = RSU5(64,16,64) - self.pool34 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage4 = RSU4(64,16,64) - self.pool45 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage5 = RSU4F(64,16,64) - self.pool56 = nn.MaxPool2D(2,stride=2,ceil_mode=True) - - self.stage6 = RSU4F(64,16,64) - - # decoder - self.stage5d = RSU4F(128,16,64) - self.stage4d = RSU4(128,16,64) - self.stage3d = RSU5(128,16,64) - self.stage2d = RSU6(128,16,64) - self.stage1d = RSU7(128,16,64) - - self.side1 = nn.Conv2D(64,out_ch,3,padding=1) - self.side2 = nn.Conv2D(64,out_ch,3,padding=1) - self.side3 = nn.Conv2D(64,out_ch,3,padding=1) - self.side4 = nn.Conv2D(64,out_ch,3,padding=1) - self.side5 = nn.Conv2D(64,out_ch,3,padding=1) - self.side6 = nn.Conv2D(64,out_ch,3,padding=1) - - self.outconv = nn.Conv2D(6,out_ch,1) - - def forward(self,x): - - hx = x - - #stage 1 - hx1 = self.stage1(hx) - hx = self.pool12(hx1) - - #stage 2 - hx2 = self.stage2(hx) - hx = self.pool23(hx2) - - #stage 3 - hx3 = self.stage3(hx) - hx = self.pool34(hx3) - - #stage 4 - hx4 = self.stage4(hx) - hx = self.pool45(hx4) - - #stage 5 - hx5 = self.stage5(hx) - hx = self.pool56(hx5) - - #stage 6 - hx6 = self.stage6(hx) - hx6up = _upsample_like(hx6,hx5) - - #decoder - hx5d = self.stage5d(paddle.concat((hx6up,hx5),1)) - hx5dup = _upsample_like(hx5d,hx4) - - hx4d = self.stage4d(paddle.concat((hx5dup,hx4),1)) - hx4dup = _upsample_like(hx4d,hx3) - - hx3d = self.stage3d(paddle.concat((hx4dup,hx3),1)) - hx3dup = _upsample_like(hx3d,hx2) - - hx2d = self.stage2d(paddle.concat((hx3dup,hx2),1)) - hx2dup = _upsample_like(hx2d,hx1) - - hx1d = self.stage1d(paddle.concat((hx2dup,hx1),1)) - - - #side output - d1 = self.side1(hx1d) - - d2 = self.side2(hx2d) - d2 = _upsample_like(d2,d1) - - d3 = self.side3(hx3d) - d3 = _upsample_like(d3,d1) - - d4 = self.side4(hx4d) - d4 = _upsample_like(d4,d1) - - d5 = self.side5(hx5d) - d5 = _upsample_like(d5,d1) - - d6 = self.side6(hx6) - d6 = _upsample_like(d6,d1) - - d0 = self.outconv(paddle.concat((d1,d2,d3,d4,d5,d6),1)) - - return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) diff --git a/modules/image/Image_gan/gan/stgan_bald/README.md b/modules/thirdparty/image/Image_gan/gan/stgan_bald/README.md similarity index 100% rename from modules/image/Image_gan/gan/stgan_bald/README.md rename to modules/thirdparty/image/Image_gan/gan/stgan_bald/README.md diff --git a/modules/image/Image_gan/gan/stgan_bald/data_feed.py b/modules/thirdparty/image/Image_gan/gan/stgan_bald/data_feed.py similarity index 100% rename from modules/image/Image_gan/gan/stgan_bald/data_feed.py rename to modules/thirdparty/image/Image_gan/gan/stgan_bald/data_feed.py diff --git a/modules/image/Image_gan/gan/stgan_bald/module.py b/modules/thirdparty/image/Image_gan/gan/stgan_bald/module.py similarity index 100% rename from modules/image/Image_gan/gan/stgan_bald/module.py rename to modules/thirdparty/image/Image_gan/gan/stgan_bald/module.py diff --git a/modules/image/Image_gan/gan/stgan_bald/module/__model__ b/modules/thirdparty/image/Image_gan/gan/stgan_bald/module/__model__ similarity index 100% rename from modules/image/Image_gan/gan/stgan_bald/module/__model__ rename to modules/thirdparty/image/Image_gan/gan/stgan_bald/module/__model__ diff --git a/modules/image/Image_gan/gan/stgan_bald/processor.py b/modules/thirdparty/image/Image_gan/gan/stgan_bald/processor.py similarity index 100% rename from modules/image/Image_gan/gan/stgan_bald/processor.py rename to modules/thirdparty/image/Image_gan/gan/stgan_bald/processor.py diff --git a/modules/image/Image_gan/gan/stgan_bald/requirements.txt b/modules/thirdparty/image/Image_gan/gan/stgan_bald/requirements.txt similarity index 100% rename from modules/image/Image_gan/gan/stgan_bald/requirements.txt rename to modules/thirdparty/image/Image_gan/gan/stgan_bald/requirements.txt diff --git a/modules/image/Image_gan/style_transfer/ID_Photo_GEN/README.md b/modules/thirdparty/image/Image_gan/style_transfer/ID_Photo_GEN/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/ID_Photo_GEN/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/ID_Photo_GEN/README.md diff --git a/modules/image/Image_gan/style_transfer/ID_Photo_GEN/module.py b/modules/thirdparty/image/Image_gan/style_transfer/ID_Photo_GEN/module.py similarity index 79% rename from modules/image/Image_gan/style_transfer/ID_Photo_GEN/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/ID_Photo_GEN/module.py index 74535b4aae191b8dd1a80f03e723f59f767f792f..eaafb6a48b2a5b9cb88babff152de6d11893b04d 100644 --- a/modules/image/Image_gan/style_transfer/ID_Photo_GEN/module.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/ID_Photo_GEN/module.py @@ -7,13 +7,14 @@ import paddle.nn as nn import paddlehub as hub from paddlehub.module.module import moduleinfo + @moduleinfo( - name="ID_Photo_GEN", # 模型名称 - type="CV", # 模型类型 - author="jm12138", # 作者名称 - author_email="jm12138@qq.com", # 作者邮箱 - summary="ID_Photo_GEN", # 模型介绍 - version="1.0.0" # 版本号 + name="ID_Photo_GEN", # 模型名称 + type="CV", # 模型类型 + author="jm12138", # 作者名称 + author_email="jm12138@qq.com", # 作者邮箱 + summary="ID_Photo_GEN", # 模型介绍 + version="1.0.0" # 版本号 ) class ID_Photo_GEN(nn.Layer): def __init__(self): @@ -38,18 +39,15 @@ class ID_Photo_GEN(nn.Layer): if images is not None: datas = images - + # 返回数据列表 return datas # 数据预处理函数 def preprocess(self, images, batch_size, use_gpu): # 获取人脸关键点 - outputs = self.face_detector.keypoint_detection( - images=images, - batch_size=batch_size, - use_gpu=use_gpu) - + outputs = self.face_detector.keypoint_detection(images=images, batch_size=batch_size, use_gpu=use_gpu) + crops = [] for output, image in zip(outputs, images): for landmarks in output['data']: @@ -58,7 +56,8 @@ class ID_Photo_GEN(nn.Layer): # rotation angle left_eye_corner = landmarks[36] right_eye_corner = landmarks[45] - radian = np.arctan((left_eye_corner[1] - right_eye_corner[1]) / (left_eye_corner[0] - right_eye_corner[0])) + radian = np.arctan( + (left_eye_corner[1] - right_eye_corner[1]) / (left_eye_corner[0] - right_eye_corner[0])) # image size after rotating height, width, _ = image.shape @@ -73,7 +72,7 @@ class ID_Photo_GEN(nn.Layer): # affine matrix M = np.array([[cos, sin, (1 - cos) * width / 2. - sin * height / 2. + Tx], - [-sin, cos, sin * width / 2. + (1 - cos) * height / 2. + Ty]]) + [-sin, cos, sin * width / 2. + (1 - cos) * height / 2. + Ty]]) image = cv2.warpAffine(image, M, (new_w, new_h), borderValue=(255, 255, 255)) @@ -103,16 +102,17 @@ class ID_Photo_GEN(nn.Layer): h, w = image.shape[:2] left_white = max(0, -left) left = max(0, left) - right = min(right, w-1) - right_white = left_white + (right-left) + right = min(right, w - 1) + right_white = left_white + (right - left) top_white = max(0, -top) top = max(0, top) - bottom = min(bottom, h-1) + bottom = min(bottom, h - 1) bottom_white = top_white + (bottom - top) - image_crop[top_white:bottom_white+1, left_white:right_white+1] = image[top:bottom+1, left:right+1].copy() + image_crop[top_white:bottom_white + 1, left_white:right_white + 1] = image[top:bottom + 1, left:right + + 1].copy() crops.append(image_crop) - + # 获取人像分割的输出 results = self.seg.Segmentation(images=crops, batch_size=batch_size) @@ -141,7 +141,7 @@ class ID_Photo_GEN(nn.Layer): cartoon = self.net(data) outputs.append(cartoon[0].numpy()) - + outputs = np.concatenate(outputs, 0) return outputs @@ -168,22 +168,11 @@ class ID_Photo_GEN(nn.Layer): cv2.imwrite(os.path.join(output_dir, 'blue_%d.jpg' % i), blue) cv2.imwrite(os.path.join(output_dir, 'red_%d.jpg' % i), red) - results.append({ - 'write': write, - 'blue': blue, - 'red': red - }) - + results.append({'write': write, 'blue': blue, 'red': red}) + return results - def Photo_GEN( - self, - images=None, - paths=None, - batch_size=1, - output_dir='output', - visualization=False, - use_gpu=False): + def Photo_GEN(self, images=None, paths=None, batch_size=1, output_dir='output', visualization=False, use_gpu=False): # 获取输入数据 images = self.load_datas(paths, images) @@ -194,4 +183,4 @@ class ID_Photo_GEN(nn.Layer): # 结果后处理 results = self.postprocess(faces, masks, visualization, output_dir) - return results \ No newline at end of file + return results diff --git a/modules/image/Image_gan/style_transfer/Photo2Cartoon/README.md b/modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/Photo2Cartoon/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/README.md diff --git a/modules/image/Image_gan/style_transfer/Photo2Cartoon/model/__init__.py b/modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/model/__init__.py similarity index 97% rename from modules/image/Image_gan/style_transfer/Photo2Cartoon/model/__init__.py rename to modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/model/__init__.py index 04de5522a2c4826b7ed6c6d67e7c8bb0857fdba0..26d196448eedc577443deb5a2fe5b0898a8fd760 100644 --- a/modules/image/Image_gan/style_transfer/Photo2Cartoon/model/__init__.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/model/__init__.py @@ -1,2 +1 @@ from .networks import ResnetGenerator - diff --git a/modules/image/Image_gan/style_transfer/Photo2Cartoon/model/networks.py b/modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/model/networks.py similarity index 78% rename from modules/image/Image_gan/style_transfer/Photo2Cartoon/model/networks.py rename to modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/model/networks.py index e6c73fcc529c6e24ad3a984b563aa5eafd254c5b..183fe33d21ffb5e678ba803322818f04e67d1f44 100644 --- a/modules/image/Image_gan/style_transfer/Photo2Cartoon/model/networks.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/model/networks.py @@ -17,72 +17,66 @@ class ResnetGenerator(nn.Layer): nn.ReLU() ] - DownBlock += [ - HourGlass(ngf, ngf), - HourGlass(ngf, ngf) - ] + DownBlock += [HourGlass(ngf, ngf), HourGlass(ngf, ngf)] # Down-Sampling n_downsampling = 2 for i in range(n_downsampling): - mult = 2 ** i + mult = 2**i DownBlock += [ nn.Pad2D([1, 1, 1, 1], 'reflect'), - nn.Conv2D(ngf*mult, ngf*mult*2, kernel_size=3, stride=2, bias_attr=False), - nn.InstanceNorm2D(ngf*mult*2, weight_attr=False, bias_attr=False), + nn.Conv2D(ngf * mult, ngf * mult * 2, kernel_size=3, stride=2, bias_attr=False), + nn.InstanceNorm2D(ngf * mult * 2, weight_attr=False, bias_attr=False), nn.ReLU() ] # Encoder Bottleneck - mult = 2 ** n_downsampling + mult = 2**n_downsampling for i in range(n_blocks): - setattr(self, 'EncodeBlock'+str(i+1), ResnetBlock(ngf*mult)) + setattr(self, 'EncodeBlock' + str(i + 1), ResnetBlock(ngf * mult)) # Class Activation Map - self.gap_fc = nn.Linear(ngf*mult, 1, bias_attr=False) - self.gmp_fc = nn.Linear(ngf*mult, 1, bias_attr=False) - self.conv1x1 = nn.Conv2D(ngf*mult*2, ngf*mult, kernel_size=1, stride=1) + self.gap_fc = nn.Linear(ngf * mult, 1, bias_attr=False) + self.gmp_fc = nn.Linear(ngf * mult, 1, bias_attr=False) + self.conv1x1 = nn.Conv2D(ngf * mult * 2, ngf * mult, kernel_size=1, stride=1) self.relu = nn.ReLU() # Gamma, Beta block FC = [] if self.light: FC += [ - nn.Linear(ngf*mult, ngf*mult, bias_attr=False), + nn.Linear(ngf * mult, ngf * mult, bias_attr=False), nn.ReLU(), - nn.Linear(ngf*mult, ngf*mult, bias_attr=False), + nn.Linear(ngf * mult, ngf * mult, bias_attr=False), nn.ReLU() ] else: FC += [ - nn.Linear(img_size//mult*img_size//mult*ngf*mult, ngf*mult, bias_attr=False), + nn.Linear(img_size // mult * img_size // mult * ngf * mult, ngf * mult, bias_attr=False), nn.ReLU(), - nn.Linear(ngf*mult, ngf*mult, bias_attr=False), + nn.Linear(ngf * mult, ngf * mult, bias_attr=False), nn.ReLU() ] # Decoder Bottleneck - mult = 2 ** n_downsampling + mult = 2**n_downsampling for i in range(n_blocks): - setattr(self, 'DecodeBlock'+str(i + 1), ResnetSoftAdaLINBlock(ngf*mult)) + setattr(self, 'DecodeBlock' + str(i + 1), ResnetSoftAdaLINBlock(ngf * mult)) # Up-Sampling UpBlock = [] for i in range(n_downsampling): - mult = 2 ** (n_downsampling - i) + mult = 2**(n_downsampling - i) UpBlock += [ nn.Upsample(scale_factor=2), nn.Pad2D([1, 1, 1, 1], 'reflect'), - nn.Conv2D(ngf*mult, ngf*mult//2, kernel_size=3, stride=1, bias_attr=False), - LIN(ngf*mult//2), + nn.Conv2D(ngf * mult, ngf * mult // 2, kernel_size=3, stride=1, bias_attr=False), + LIN(ngf * mult // 2), nn.ReLU() ] - UpBlock += [ - HourGlass(ngf, ngf), - HourGlass(ngf, ngf, False) - ] + UpBlock += [HourGlass(ngf, ngf), HourGlass(ngf, ngf, False)] UpBlock += [ nn.Pad2D([3, 3, 3, 3], 'reflect'), @@ -101,7 +95,7 @@ class ResnetGenerator(nn.Layer): content_features = [] for i in range(self.n_blocks): - x = getattr(self, 'EncodeBlock'+str(i+1))(x) + x = getattr(self, 'EncodeBlock' + str(i + 1))(x) content_features.append(F.adaptive_avg_pool2d(x, 1).reshape([bs, -1])) gap = F.adaptive_avg_pool2d(x, 1) @@ -127,7 +121,7 @@ class ResnetGenerator(nn.Layer): style_features = self.FC(x.reshape([bs, -1])) for i in range(self.n_blocks): - x = getattr(self, 'DecodeBlock'+str(i+1))(x, content_features[4-i-1], style_features) + x = getattr(self, 'DecodeBlock' + str(i + 1))(x, content_features[4 - i - 1], style_features) out = self.UpBlock(x) @@ -140,25 +134,20 @@ class ConvBlock(nn.Layer): self.dim_in = dim_in self.dim_out = dim_out - self.conv_block1 = self.__convblock(dim_in, dim_out//2) - self.conv_block2 = self.__convblock(dim_out//2, dim_out//4) - self.conv_block3 = self.__convblock(dim_out//4, dim_out//4) + self.conv_block1 = self.__convblock(dim_in, dim_out // 2) + self.conv_block2 = self.__convblock(dim_out // 2, dim_out // 4) + self.conv_block3 = self.__convblock(dim_out // 4, dim_out // 4) if self.dim_in != self.dim_out: self.conv_skip = nn.Sequential( - nn.InstanceNorm2D(dim_in, weight_attr=False, bias_attr=False), - nn.ReLU(), - nn.Conv2D(dim_in, dim_out, kernel_size=1, stride=1, bias_attr=False) - ) + nn.InstanceNorm2D(dim_in, weight_attr=False, bias_attr=False), nn.ReLU(), + nn.Conv2D(dim_in, dim_out, kernel_size=1, stride=1, bias_attr=False)) @staticmethod def __convblock(dim_in, dim_out): return nn.Sequential( - nn.InstanceNorm2D(dim_in, weight_attr=False, bias_attr=False), - nn.ReLU(), - nn.Pad2D([1, 1, 1, 1], 'reflect'), - nn.Conv2D(dim_in, dim_out, kernel_size=3, stride=1, bias_attr=False) - ) + nn.InstanceNorm2D(dim_in, weight_attr=False, bias_attr=False), nn.ReLU(), nn.Pad2D([1, 1, 1, 1], 'reflect'), + nn.Conv2D(dim_in, dim_out, kernel_size=3, stride=1, bias_attr=False)) def forward(self, x): residual = x @@ -182,24 +171,24 @@ class HourGlassBlock(nn.Layer): self.n_block = 9 for i in range(self.n_skip): - setattr(self, 'ConvBlockskip'+str(i+1), ConvBlock(dim_in, dim_in)) + setattr(self, 'ConvBlockskip' + str(i + 1), ConvBlock(dim_in, dim_in)) for i in range(self.n_block): - setattr(self, 'ConvBlock'+str(i+1), ConvBlock(dim_in, dim_in)) + setattr(self, 'ConvBlock' + str(i + 1), ConvBlock(dim_in, dim_in)) def forward(self, x): skips = [] for i in range(self.n_skip): - skips.append(getattr(self, 'ConvBlockskip'+str(i+1))(x)) + skips.append(getattr(self, 'ConvBlockskip' + str(i + 1))(x)) x = F.avg_pool2d(x, 2) - x = getattr(self, 'ConvBlock'+str(i+1))(x) + x = getattr(self, 'ConvBlock' + str(i + 1))(x) x = self.ConvBlock5(x) for i in range(self.n_skip): - x = getattr(self, 'ConvBlock'+str(i+6))(x) + x = getattr(self, 'ConvBlock' + str(i + 6))(x) x = F.upsample(x, scale_factor=2) - x = skips[self.n_skip-i-1] + x + x = skips[self.n_skip - i - 1] + x return x @@ -210,12 +199,9 @@ class HourGlass(nn.Layer): self.use_res = use_res self.HG = nn.Sequential( - HourGlassBlock(dim_in), - ConvBlock(dim_out, dim_out), + HourGlassBlock(dim_in), ConvBlock(dim_out, dim_out), nn.Conv2D(dim_out, dim_out, kernel_size=1, stride=1, bias_attr=False), - nn.InstanceNorm2D(dim_out, weight_attr=False, bias_attr=False), - nn.ReLU() - ) + nn.InstanceNorm2D(dim_out, weight_attr=False, bias_attr=False), nn.ReLU()) self.Conv1 = nn.Conv2D(dim_out, 3, kernel_size=1, stride=1) @@ -292,12 +278,12 @@ class SoftAdaLIN(nn.Layer): self.w_gamma = self.create_parameter([1, num_features], default_initializer=nn.initializer.Constant(0.)) self.w_beta = self.create_parameter([1, num_features], default_initializer=nn.initializer.Constant(0.)) - self.c_gamma = nn.Sequential(nn.Linear(num_features, num_features, bias_attr=False), - nn.ReLU(), - nn.Linear(num_features, num_features, bias_attr=False)) - self.c_beta = nn.Sequential(nn.Linear(num_features, num_features, bias_attr=False), - nn.ReLU(), - nn.Linear(num_features, num_features, bias_attr=False)) + self.c_gamma = nn.Sequential( + nn.Linear(num_features, num_features, bias_attr=False), nn.ReLU(), + nn.Linear(num_features, num_features, bias_attr=False)) + self.c_beta = nn.Sequential( + nn.Linear(num_features, num_features, bias_attr=False), nn.ReLU(), + nn.Linear(num_features, num_features, bias_attr=False)) self.s_gamma = nn.Linear(num_features, num_features, bias_attr=False) self.s_beta = nn.Linear(num_features, num_features, bias_attr=False) @@ -352,8 +338,8 @@ class LIN(nn.Layer): out = out * self.gamma.expand([x.shape[0], -1, -1, -1]) + self.beta.expand([x.shape[0], -1, -1, -1]) return out - - + + if __name__ == '__main__': #d = Discriminator(3) # paddle.summary(d, (4, 3, 256, 256)) diff --git a/modules/image/Image_gan/style_transfer/Photo2Cartoon/module.py b/modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/module.py similarity index 80% rename from modules/image/Image_gan/style_transfer/Photo2Cartoon/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/module.py index feabf1ca0399520572087f995cc365543ee86092..d2a6d7b723e46800b790642fc5a98b6657bfad98 100644 --- a/modules/image/Image_gan/style_transfer/Photo2Cartoon/module.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/Photo2Cartoon/module.py @@ -8,13 +8,14 @@ import paddlehub as hub from Photo2Cartoon.model import ResnetGenerator from paddlehub.module.module import moduleinfo + @moduleinfo( - name="Photo2Cartoon", # 模型名称 - type="CV", # 模型类型 - author="jm12138", # 作者名称 - author_email="jm12138@qq.com", # 作者邮箱 - summary="Photo2Cartoon", # 模型介绍 - version="1.0.0" # 版本号 + name="Photo2Cartoon", # 模型名称 + type="CV", # 模型类型 + author="jm12138", # 作者名称 + author_email="jm12138@qq.com", # 作者邮箱 + summary="Photo2Cartoon", # 模型介绍 + version="1.0.0" # 版本号 ) class Photo2Cartoon(nn.Layer): def __init__(self): @@ -49,18 +50,15 @@ class Photo2Cartoon(nn.Layer): if images is not None: datas = images - + # 返回数据列表 return datas # 数据预处理函数 def preprocess(self, images, batch_size, use_gpu): # 获取人脸关键点 - outputs = self.face_detector.keypoint_detection( - images=images, - batch_size=batch_size, - use_gpu=use_gpu) - + outputs = self.face_detector.keypoint_detection(images=images, batch_size=batch_size, use_gpu=use_gpu) + crops = [] for output, image in zip(outputs, images): for landmarks in output['data']: @@ -69,7 +67,8 @@ class Photo2Cartoon(nn.Layer): # rotation angle left_eye_corner = landmarks[36] right_eye_corner = landmarks[45] - radian = np.arctan((left_eye_corner[1] - right_eye_corner[1]) / (left_eye_corner[0] - right_eye_corner[0])) + radian = np.arctan( + (left_eye_corner[1] - right_eye_corner[1]) / (left_eye_corner[0] - right_eye_corner[0])) # image size after rotating height, width, _ = image.shape @@ -84,7 +83,7 @@ class Photo2Cartoon(nn.Layer): # affine matrix M = np.array([[cos, sin, (1 - cos) * width / 2. - sin * height / 2. + Tx], - [-sin, cos, sin * width / 2. + (1 - cos) * height / 2. + Ty]]) + [-sin, cos, sin * width / 2. + (1 - cos) * height / 2. + Ty]]) image = cv2.warpAffine(image, M, (new_w, new_h), borderValue=(255, 255, 255)) @@ -114,16 +113,17 @@ class Photo2Cartoon(nn.Layer): h, w = image.shape[:2] left_white = max(0, -left) left = max(0, left) - right = min(right, w-1) - right_white = left_white + (right-left) + right = min(right, w - 1) + right_white = left_white + (right - left) top_white = max(0, -top) top = max(0, top) - bottom = min(bottom, h-1) + bottom = min(bottom, h - 1) bottom_white = top_white + (bottom - top) - image_crop[top_white:bottom_white+1, left_white:right_white+1] = image[top:bottom+1, left:right+1].copy() + image_crop[top_white:bottom_white + 1, left_white:right_white + 1] = image[top:bottom + 1, left:right + + 1].copy() crops.append(image_crop) - + # 获取人像分割的输出 results = self.seg.Segmentation(images=crops, batch_size=batch_size) @@ -158,7 +158,7 @@ class Photo2Cartoon(nn.Layer): # 切分数据 datas_num = input_datas.shape[0] - split_num = datas_num//batch_size+1 if datas_num%batch_size!=0 else datas_num//batch_size + split_num = datas_num // batch_size + 1 if datas_num % batch_size != 0 else datas_num // batch_size input_datas = np.array_split(input_datas, split_num) return input_datas, masks @@ -175,7 +175,7 @@ class Photo2Cartoon(nn.Layer): cartoon = self.net(data) outputs.append(cartoon[0].numpy()) - + outputs = np.concatenate(outputs, 0) return outputs @@ -204,17 +204,16 @@ class Photo2Cartoon(nn.Layer): cv2.imwrite(os.path.join(output_dir, 'result_%d.png' % i), cartoon) cartoons.append(cartoon) - + return cartoons - def Cartoon_GEN( - self, - images=None, - paths=None, - batch_size=1, - output_dir='output', - visualization=False, - use_gpu=False): + def Cartoon_GEN(self, + images=None, + paths=None, + batch_size=1, + output_dir='output', + visualization=False, + use_gpu=False): # 获取输入数据 images = self.load_datas(paths, images) @@ -228,4 +227,4 @@ class Photo2Cartoon(nn.Layer): # 结果后处理 cartoons = self.postprocess(outputs, masks, visualization, output_dir) - return cartoons \ No newline at end of file + return cartoons diff --git a/modules/image/Image_gan/style_transfer/U2Net_Portrait/README.md b/modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/U2Net_Portrait/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/README.md diff --git a/modules/image/Image_gan/style_transfer/U2Net_Portrait/module.py b/modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/module.py similarity index 61% rename from modules/image/Image_gan/style_transfer/U2Net_Portrait/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/module.py index 1135c5e6303424f910a9108be4ba20ba47705f1f..5d4fe32412a5e722f2822300a51b55376beb4bd1 100644 --- a/modules/image/Image_gan/style_transfer/U2Net_Portrait/module.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/module.py @@ -6,18 +6,19 @@ from U2Net_Portrait.u2net import U2NET from U2Net_Portrait.processor import Processor from paddlehub.module.module import moduleinfo + @moduleinfo( - name="U2Net_Portrait", # 模型名称 - type="CV", # 模型类型 - author="jm12138", # 作者名称 - author_email="jm12138@qq.com", # 作者邮箱 - summary="U2Net_Portrait", # 模型介绍 - version="1.0.0" # 版本号 + name="U2Net_Portrait", # 模型名称 + type="CV", # 模型类型 + author="jm12138", # 作者名称 + author_email="jm12138@qq.com", # 作者邮箱 + summary="U2Net_Portrait", # 模型介绍 + version="1.0.0" # 版本号 ) class U2Net_Portrait(nn.Layer): def __init__(self): super(U2Net_Portrait, self).__init__() - self.model = U2NET(3,1) + self.model = U2NET(3, 1) state_dict = paddle.load(os.path.join(self.directory, 'u2net_portrait.pdparams')) self.model.set_dict(state_dict) self.model.eval() @@ -26,22 +27,21 @@ class U2Net_Portrait(nn.Layer): outputs = [] for data in input_datas: data = paddle.to_tensor(data, 'float32') - d1,d2,d3,d4,d5,d6,d7= self.model(data) + d1, d2, d3, d4, d5, d6, d7 = self.model(data) outputs.append(d1.numpy()) outputs = np.concatenate(outputs, 0) - + return outputs - def Portrait_GEN( - self, - images=None, - paths=None, - scale=1, - batch_size=1, - output_dir='output', - face_detection=True, - visualization=False): + def Portrait_GEN(self, + images=None, + paths=None, + scale=1, + batch_size=1, + output_dir='output', + face_detection=True, + visualization=False): # 初始化数据处理器 processor = Processor(paths, images, batch_size, face_detection, scale) diff --git a/modules/image/Image_gan/style_transfer/U2Net_Portrait/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/processor.py similarity index 54% rename from modules/image/Image_gan/style_transfer/U2Net_Portrait/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/processor.py index e379a6ec8a8a445ac445e7cde849d5e5d6905edd..73ef7a783539c727da9c105a7096a01b8a4ff23f 100644 --- a/modules/image/Image_gan/style_transfer/U2Net_Portrait/processor.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/processor.py @@ -5,6 +5,7 @@ import paddlehub as hub __all__ = ['Processor'] + class Processor(): def __init__(self, paths, images, batch_size, face_detection=True, scale=1): # 图像列表 @@ -26,7 +27,7 @@ class Processor(): if images is not None: datas = images - + # 返回数据列表 return datas @@ -35,10 +36,7 @@ class Processor(): if face_detection: # face detection face_detector = hub.Module(name="pyramidbox_lite_mobile") - results = face_detector.face_detection(images=imgs, - use_gpu=False, - visualization=False, - confs_threshold=0.5) + results = face_detector.face_detection(images=imgs, use_gpu=False, visualization=False, confs_threshold=0.5) im_faces = [] for datas, img in zip(results, imgs): for face in datas['data']: @@ -46,52 +44,64 @@ class Processor(): l, r, t, b = [face['left'], face['right'], face['top'], face['bottom']] # square crop - pad = max(int(scale*(r-l)), int(scale*(b-t))) - c_w, c_h = (r-l)//2+l, (b-t)//2+t - top = 0 if c_h-pad<0 else c_h-pad + pad = max(int(scale * (r - l)), int(scale * (b - t))) + c_w, c_h = (r - l) // 2 + l, (b - t) // 2 + t + top = 0 if c_h - pad < 0 else c_h - pad bottom = pad + c_h - left = 0 if c_w-pad<0 else c_w-pad + left = 0 if c_w - pad < 0 else c_w - pad right = pad + c_w crop = img[top:bottom, left:right] - + # resize - im_face = cv2.resize(crop, (512,512), interpolation = cv2.INTER_AREA) + im_face = cv2.resize(crop, (512, 512), interpolation=cv2.INTER_AREA) im_faces.append(im_face) else: im_faces = [] for img in imgs: h, w = img.shape[:2] - if h>w: - if (h-w)%2==0: - img = np.pad(img,((0,0),((h-w)//2,(h-w)//2),(0,0)),mode='constant',constant_values=((255,255),(255,255),(255,255))) + if h > w: + if (h - w) % 2 == 0: + img = np.pad( + img, ((0, 0), ((h - w) // 2, (h - w) // 2), (0, 0)), + mode='constant', + constant_values=((255, 255), (255, 255), (255, 255))) else: - img = np.pad(img,((0,0),((h-w)//2,(h-w)//2+1),(0,0)),mode='constant',constant_values=((255,255),(255,255),(255,255))) + img = np.pad( + img, ((0, 0), ((h - w) // 2, (h - w) // 2 + 1), (0, 0)), + mode='constant', + constant_values=((255, 255), (255, 255), (255, 255))) else: - if (w-h)%2==0: - img = np.pad(img,(((w-h)//2,(w-h)//2),(0,0),(0,0)),mode='constant',constant_values=((255,255),(255,255),(255,255))) + if (w - h) % 2 == 0: + img = np.pad( + img, (((w - h) // 2, (w - h) // 2), (0, 0), (0, 0)), + mode='constant', + constant_values=((255, 255), (255, 255), (255, 255))) else: - img = np.pad(img,(((w-h)//2,(w-h)//2+1),(0,0),(0,0)),mode='constant',constant_values=((255,255),(255,255),(255,255))) - im_face = cv2.resize(img, (512,512), interpolation = cv2.INTER_AREA) + img = np.pad( + img, (((w - h) // 2, (w - h) // 2 + 1), (0, 0), (0, 0)), + mode='constant', + constant_values=((255, 255), (255, 255), (255, 255))) + im_face = cv2.resize(img, (512, 512), interpolation=cv2.INTER_AREA) im_faces.append(im_face) input_datas = [] for im_face in im_faces: - tmpImg = np.zeros((im_face.shape[0],im_face.shape[1],3)) - im_face = im_face/np.max(im_face) + tmpImg = np.zeros((im_face.shape[0], im_face.shape[1], 3)) + im_face = im_face / np.max(im_face) - tmpImg[:,:,0] = (im_face[:,:,2]-0.406)/0.225 - tmpImg[:,:,1] = (im_face[:,:,1]-0.456)/0.224 - tmpImg[:,:,2] = (im_face[:,:,0]-0.485)/0.229 + tmpImg[:, :, 0] = (im_face[:, :, 2] - 0.406) / 0.225 + tmpImg[:, :, 1] = (im_face[:, :, 1] - 0.456) / 0.224 + tmpImg[:, :, 2] = (im_face[:, :, 0] - 0.485) / 0.229 # convert BGR to RGB tmpImg = tmpImg.transpose((2, 0, 1)) - tmpImg = tmpImg[np.newaxis,:,:,:] + tmpImg = tmpImg[np.newaxis, :, :, :] input_datas.append(tmpImg) - + input_datas = np.concatenate(input_datas, 0) datas_num = input_datas.shape[0] - split_num = datas_num//batch_size+1 if datas_num%batch_size!=0 else datas_num//batch_size + split_num = datas_num // batch_size + 1 if datas_num % batch_size != 0 else datas_num // batch_size input_datas = np.array_split(input_datas, split_num) @@ -101,7 +111,7 @@ class Processor(): ma = np.max(d) mi = np.min(d) - dn = (d-mi)/(ma-mi) + dn = (d - mi) / (ma - mi) return dn @@ -110,20 +120,20 @@ class Processor(): results = [] if visualization and not os.path.exists(output_dir): os.mkdir(output_dir) - + for i in range(outputs.shape[0]): # normalization - pred = 1.0 - outputs[i,0,:,:] + pred = 1.0 - outputs[i, 0, :, :] pred = self.normPRED(pred) # convert torch tensor to numpy array pred = pred.squeeze() - pred = (pred*255).astype(np.uint8) + pred = (pred * 255).astype(np.uint8) results.append(pred) if visualization: cv2.imwrite(os.path.join(output_dir, 'result_%d.png' % i), pred) - return results \ No newline at end of file + return results diff --git a/modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/u2net.py b/modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/u2net.py new file mode 100644 index 0000000000000000000000000000000000000000..3a7ecd0e90d4386df33f532833ceca48fc0d62a0 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/U2Net_Portrait/u2net.py @@ -0,0 +1,524 @@ +import paddle +import paddle.nn as nn +import paddle.nn.functional as F + +__all__ = ['U2NETP', 'U2NET'] + + +class REBNCONV(nn.Layer): + def __init__(self, in_ch=3, out_ch=3, dirate=1): + super(REBNCONV, self).__init__() + + self.conv_s1 = nn.Conv2D(in_ch, out_ch, 3, padding=1 * dirate, dilation=1 * dirate) + self.bn_s1 = nn.BatchNorm2D(out_ch) + self.relu_s1 = nn.ReLU() + + def forward(self, x): + + hx = x + xout = self.relu_s1(self.bn_s1(self.conv_s1(hx))) + + return xout + + +## upsample tensor 'src' to have the same spatial size with tensor 'tar' +def _upsample_like(src, tar): + + src = F.upsample(src, size=tar.shape[2:], mode='bilinear') + + return src + + +### RSU-7 ### +class RSU7(nn.Layer): #UNet07DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU7, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool4 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool5 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv7 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv6d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + hx = self.pool4(hx4) + + hx5 = self.rebnconv5(hx) + hx = self.pool5(hx5) + + hx6 = self.rebnconv6(hx) + + hx7 = self.rebnconv7(hx6) + + hx6d = self.rebnconv6d(paddle.concat((hx7, hx6), 1)) + hx6dup = _upsample_like(hx6d, hx5) + + hx5d = self.rebnconv5d(paddle.concat((hx6dup, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-6 ### +class RSU6(nn.Layer): #UNet06DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU6, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool4 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + hx = self.pool4(hx4) + + hx5 = self.rebnconv5(hx) + + hx6 = self.rebnconv6(hx5) + + hx5d = self.rebnconv5d(paddle.concat((hx6, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-5 ### +class RSU5(nn.Layer): #UNet05DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU5, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + + hx5 = self.rebnconv5(hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-4 ### +class RSU4(nn.Layer): #UNet04DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU4, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + + hx4 = self.rebnconv4(hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-4F ### +class RSU4F(nn.Layer): #UNet04FRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU4F, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=2) + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=4) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=8) + + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=4) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=2) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx2 = self.rebnconv2(hx1) + hx3 = self.rebnconv3(hx2) + + hx4 = self.rebnconv4(hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4, hx3), 1)) + hx2d = self.rebnconv2d(paddle.concat((hx3d, hx2), 1)) + hx1d = self.rebnconv1d(paddle.concat((hx2d, hx1), 1)) + + return hx1d + hxin + + +##### U^2-Net #### +class U2NET(nn.Layer): + def __init__(self, in_ch=3, out_ch=1): + super(U2NET, self).__init__() + + self.stage1 = RSU7(in_ch, 32, 64) + self.pool12 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage2 = RSU6(64, 32, 128) + self.pool23 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage3 = RSU5(128, 64, 256) + self.pool34 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage4 = RSU4(256, 128, 512) + self.pool45 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage5 = RSU4F(512, 256, 512) + self.pool56 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage6 = RSU4F(512, 256, 512) + + # decoder + self.stage5d = RSU4F(1024, 256, 512) + self.stage4d = RSU4(1024, 128, 256) + self.stage3d = RSU5(512, 64, 128) + self.stage2d = RSU6(256, 32, 64) + self.stage1d = RSU7(128, 16, 64) + + self.side1 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side2 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side3 = nn.Conv2D(128, out_ch, 3, padding=1) + self.side4 = nn.Conv2D(256, out_ch, 3, padding=1) + self.side5 = nn.Conv2D(512, out_ch, 3, padding=1) + self.side6 = nn.Conv2D(512, out_ch, 3, padding=1) + + self.outconv = nn.Conv2D(6, out_ch, 1) + + def forward(self, x): + + hx = x + + #stage 1 + hx1 = self.stage1(hx) + hx = self.pool12(hx1) + + #stage 2 + hx2 = self.stage2(hx) + hx = self.pool23(hx2) + + #stage 3 + hx3 = self.stage3(hx) + hx = self.pool34(hx3) + + #stage 4 + hx4 = self.stage4(hx) + hx = self.pool45(hx4) + + #stage 5 + hx5 = self.stage5(hx) + hx = self.pool56(hx5) + + #stage 6 + hx6 = self.stage6(hx) + hx6up = _upsample_like(hx6, hx5) + + #-------------------- decoder -------------------- + hx5d = self.stage5d(paddle.concat((hx6up, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.stage4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.stage3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.stage2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.stage1d(paddle.concat((hx2dup, hx1), 1)) + + #side output + d1 = self.side1(hx1d) + + d2 = self.side2(hx2d) + d2 = _upsample_like(d2, d1) + + d3 = self.side3(hx3d) + d3 = _upsample_like(d3, d1) + + d4 = self.side4(hx4d) + d4 = _upsample_like(d4, d1) + + d5 = self.side5(hx5d) + d5 = _upsample_like(d5, d1) + + d6 = self.side6(hx6) + d6 = _upsample_like(d6, d1) + + d0 = self.outconv(paddle.concat((d1, d2, d3, d4, d5, d6), 1)) + + return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) + + +### U^2-Net small ### +class U2NETP(nn.Layer): + def __init__(self, in_ch=3, out_ch=1): + super(U2NETP, self).__init__() + + self.stage1 = RSU7(in_ch, 16, 64) + self.pool12 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage2 = RSU6(64, 16, 64) + self.pool23 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage3 = RSU5(64, 16, 64) + self.pool34 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage4 = RSU4(64, 16, 64) + self.pool45 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage5 = RSU4F(64, 16, 64) + self.pool56 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage6 = RSU4F(64, 16, 64) + + # decoder + self.stage5d = RSU4F(128, 16, 64) + self.stage4d = RSU4(128, 16, 64) + self.stage3d = RSU5(128, 16, 64) + self.stage2d = RSU6(128, 16, 64) + self.stage1d = RSU7(128, 16, 64) + + self.side1 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side2 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side3 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side4 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side5 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side6 = nn.Conv2D(64, out_ch, 3, padding=1) + + self.outconv = nn.Conv2D(6, out_ch, 1) + + def forward(self, x): + + hx = x + + #stage 1 + hx1 = self.stage1(hx) + hx = self.pool12(hx1) + + #stage 2 + hx2 = self.stage2(hx) + hx = self.pool23(hx2) + + #stage 3 + hx3 = self.stage3(hx) + hx = self.pool34(hx3) + + #stage 4 + hx4 = self.stage4(hx) + hx = self.pool45(hx4) + + #stage 5 + hx5 = self.stage5(hx) + hx = self.pool56(hx5) + + #stage 6 + hx6 = self.stage6(hx) + hx6up = _upsample_like(hx6, hx5) + + #decoder + hx5d = self.stage5d(paddle.concat((hx6up, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.stage4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.stage3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.stage2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.stage1d(paddle.concat((hx2dup, hx1), 1)) + + #side output + d1 = self.side1(hx1d) + + d2 = self.side2(hx2d) + d2 = _upsample_like(d2, d1) + + d3 = self.side3(hx3d) + d3 = _upsample_like(d3, d1) + + d4 = self.side4(hx4d) + d4 = _upsample_like(d4, d1) + + d5 = self.side5(hx5d) + d5 = _upsample_like(d5, d1) + + d6 = self.side6(hx6) + d6 = _upsample_like(d6, d1) + + d0 = self.outconv(paddle.concat((d1, d2, d3, d4, d5, d6), 1)) + + return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) diff --git a/modules/image/Image_gan/style_transfer/UGATIT_100w/README.md b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_100w/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/README.md diff --git a/modules/image/Image_gan/style_transfer/UGATIT_100w/model.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/model.py similarity index 91% rename from modules/image/Image_gan/style_transfer/UGATIT_100w/model.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/model.py index 3adadc9232afaaafe31b3520ad54db406bc42229..e7a1b366a191c04309038546da359bc16ebe0651 100644 --- a/modules/image/Image_gan/style_transfer/UGATIT_100w/model.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/model.py @@ -5,6 +5,7 @@ from paddle.inference import create_predictor, Config __all__ = ['Model'] + class Model(): # 初始化函数 def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): @@ -24,9 +25,11 @@ class Model(): try: int(os.environ.get('CUDA_VISIBLE_DEVICES')) except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) use_gpu = False - + # 加载模型参数 if combined: model = os.path.join(modelpath, "__model__") @@ -36,7 +39,7 @@ class Model(): config = Config(modelpath) # 设置参数 - if use_gpu: + if use_gpu: config.enable_use_gpu(100, 0) else: config.disable_gpu() @@ -47,10 +50,10 @@ class Model(): config.enable_memory_optim() config.switch_use_feed_fetch_ops(False) config.switch_specify_input_names(True) - + # 通过参数加载模型预测器 predictor = create_predictor(config) - + # 返回预测器 return predictor @@ -65,9 +68,9 @@ class Model(): self.predictor.run() output = self.output_handle.copy_to_cpu() outputs.append(output) - + # 预测结果合并 outputs = np.concatenate(outputs, 0) # 返回预测结果 - return outputs \ No newline at end of file + return outputs diff --git a/modules/image/Image_gan/style_transfer/UGATIT_100w/module.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_100w/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/module.py diff --git a/modules/image/Image_gan/style_transfer/UGATIT_100w/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_100w/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_100w/processor.py diff --git a/modules/image/Image_gan/style_transfer/UGATIT_83w/README.md b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_83w/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/README.md diff --git a/modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/model.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/model.py similarity index 91% rename from modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/model.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/model.py index 3adadc9232afaaafe31b3520ad54db406bc42229..e7a1b366a191c04309038546da359bc16ebe0651 100644 --- a/modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/model.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/model.py @@ -5,6 +5,7 @@ from paddle.inference import create_predictor, Config __all__ = ['Model'] + class Model(): # 初始化函数 def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): @@ -24,9 +25,11 @@ class Model(): try: int(os.environ.get('CUDA_VISIBLE_DEVICES')) except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) use_gpu = False - + # 加载模型参数 if combined: model = os.path.join(modelpath, "__model__") @@ -36,7 +39,7 @@ class Model(): config = Config(modelpath) # 设置参数 - if use_gpu: + if use_gpu: config.enable_use_gpu(100, 0) else: config.disable_gpu() @@ -47,10 +50,10 @@ class Model(): config.enable_memory_optim() config.switch_use_feed_fetch_ops(False) config.switch_specify_input_names(True) - + # 通过参数加载模型预测器 predictor = create_predictor(config) - + # 返回预测器 return predictor @@ -65,9 +68,9 @@ class Model(): self.predictor.run() output = self.output_handle.copy_to_cpu() outputs.append(output) - + # 预测结果合并 outputs = np.concatenate(outputs, 0) # 返回预测结果 - return outputs \ No newline at end of file + return outputs diff --git a/modules/image/Image_gan/style_transfer/UGATIT_83w/module.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_83w/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/module.py diff --git a/modules/image/Image_gan/style_transfer/UGATIT_83w/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_83w/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_83w/processor.py diff --git a/modules/image/Image_gan/style_transfer/UGATIT_92w/README.md b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_92w/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/README.md diff --git a/modules/image/Image_gan/style_transfer/UGATIT_92w/model.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/model.py similarity index 91% rename from modules/image/Image_gan/style_transfer/UGATIT_92w/model.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/model.py index 3adadc9232afaaafe31b3520ad54db406bc42229..e7a1b366a191c04309038546da359bc16ebe0651 100644 --- a/modules/image/Image_gan/style_transfer/UGATIT_92w/model.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/model.py @@ -5,6 +5,7 @@ from paddle.inference import create_predictor, Config __all__ = ['Model'] + class Model(): # 初始化函数 def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): @@ -24,9 +25,11 @@ class Model(): try: int(os.environ.get('CUDA_VISIBLE_DEVICES')) except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) use_gpu = False - + # 加载模型参数 if combined: model = os.path.join(modelpath, "__model__") @@ -36,7 +39,7 @@ class Model(): config = Config(modelpath) # 设置参数 - if use_gpu: + if use_gpu: config.enable_use_gpu(100, 0) else: config.disable_gpu() @@ -47,10 +50,10 @@ class Model(): config.enable_memory_optim() config.switch_use_feed_fetch_ops(False) config.switch_specify_input_names(True) - + # 通过参数加载模型预测器 predictor = create_predictor(config) - + # 返回预测器 return predictor @@ -65,9 +68,9 @@ class Model(): self.predictor.run() output = self.output_handle.copy_to_cpu() outputs.append(output) - + # 预测结果合并 outputs = np.concatenate(outputs, 0) # 返回预测结果 - return outputs \ No newline at end of file + return outputs diff --git a/modules/image/Image_gan/style_transfer/UGATIT_92w/module.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_92w/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/module.py diff --git a/modules/image/Image_gan/style_transfer/UGATIT_92w/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/UGATIT_92w/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/UGATIT_92w/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/README.md diff --git a/modules/image/Image_gan/style_transfer/UGATIT_83w/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/model.py similarity index 91% rename from modules/image/Image_gan/style_transfer/UGATIT_83w/model.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/model.py index 3adadc9232afaaafe31b3520ad54db406bc42229..e7a1b366a191c04309038546da359bc16ebe0651 100644 --- a/modules/image/Image_gan/style_transfer/UGATIT_83w/model.py +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/model.py @@ -5,6 +5,7 @@ from paddle.inference import create_predictor, Config __all__ = ['Model'] + class Model(): # 初始化函数 def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): @@ -24,9 +25,11 @@ class Model(): try: int(os.environ.get('CUDA_VISIBLE_DEVICES')) except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) use_gpu = False - + # 加载模型参数 if combined: model = os.path.join(modelpath, "__model__") @@ -36,7 +39,7 @@ class Model(): config = Config(modelpath) # 设置参数 - if use_gpu: + if use_gpu: config.enable_use_gpu(100, 0) else: config.disable_gpu() @@ -47,10 +50,10 @@ class Model(): config.enable_memory_optim() config.switch_use_feed_fetch_ops(False) config.switch_specify_input_names(True) - + # 通过参数加载模型预测器 predictor = create_predictor(config) - + # 返回预测器 return predictor @@ -65,9 +68,9 @@ class Model(): self.predictor.run() output = self.output_handle.copy_to_cpu() outputs.append(output) - + # 预测结果合并 outputs = np.concatenate(outputs, 0) # 返回预测结果 - return outputs \ No newline at end of file + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v1_hayao_60/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v1_hayao_60/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/README.md diff --git a/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/model.py new file mode 100644 index 0000000000000000000000000000000000000000..e7a1b366a191c04309038546da359bc16ebe0651 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_hayao_64/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_64/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/README.md diff --git a/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/model.py new file mode 100644 index 0000000000000000000000000000000000000000..e7a1b366a191c04309038546da359bc16ebe0651 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_hayao_99/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_hayao_99/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/README.md diff --git a/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/model.py new file mode 100644 index 0000000000000000000000000000000000000000..e7a1b366a191c04309038546da359bc16ebe0651 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_54/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_54/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/README.md diff --git a/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/model.py new file mode 100644 index 0000000000000000000000000000000000000000..e7a1b366a191c04309038546da359bc16ebe0651 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_74/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_74/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/README.md diff --git a/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/model.py new file mode 100644 index 0000000000000000000000000000000000000000..e7a1b366a191c04309038546da359bc16ebe0651 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_97/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_97/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/README.md diff --git a/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/model.py new file mode 100644 index 0000000000000000000000000000000000000000..e7a1b366a191c04309038546da359bc16ebe0651 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_paprika_98/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_paprika_98/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/README.md diff --git a/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/model.py new file mode 100644 index 0000000000000000000000000000000000000000..e7a1b366a191c04309038546da359bc16ebe0651 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_shinkai_33/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_33/processor.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/README.md b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/README.md similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/README.md rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/README.md diff --git a/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/model.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/model.py new file mode 100644 index 0000000000000000000000000000000000000000..e7a1b366a191c04309038546da359bc16ebe0651 --- /dev/null +++ b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/module.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/module.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/module.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/module.py diff --git a/modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/processor.py b/modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/processor.py similarity index 100% rename from modules/image/Image_gan/style_transfer/animegan_v2_shinkai_53/processor.py rename to modules/thirdparty/image/Image_gan/style_transfer/animegan_v2_shinkai_53/processor.py diff --git a/modules/image/depth_estimation/MiDaS_Large/README.md b/modules/thirdparty/image/depth_estimation/MiDaS_Large/README.md similarity index 100% rename from modules/image/depth_estimation/MiDaS_Large/README.md rename to modules/thirdparty/image/depth_estimation/MiDaS_Large/README.md diff --git a/modules/image/depth_estimation/MiDaS_Large/inference.py b/modules/thirdparty/image/depth_estimation/MiDaS_Large/inference.py similarity index 86% rename from modules/image/depth_estimation/MiDaS_Large/inference.py rename to modules/thirdparty/image/depth_estimation/MiDaS_Large/inference.py index 6ebe297ae4c921e07190c6375e07ecaba0d85a8c..f3a2f3c2f03dc723be6cefba5d51e83ca47bdd17 100644 --- a/modules/image/depth_estimation/MiDaS_Large/inference.py +++ b/modules/thirdparty/image/depth_estimation/MiDaS_Large/inference.py @@ -5,6 +5,7 @@ from paddle.inference import create_predictor, Config __all__ = ['InferenceModel'] + class InferenceModel(): # 初始化函数 def __init__(self, modelpath, use_gpu=False, use_mkldnn=False, combined=True): @@ -25,14 +26,10 @@ class InferenceModel(): # 打印函数 def __repr__(self): ''' - get the numbers and name of inputs and outputs + get the numbers and name of inputs and outputs ''' - return 'inputs_num: %d\ninputs_names: %s\noutputs_num: %d\noutputs_names: %s' % ( - len(self.input_handles), - str(self.input_names), - len(self.output_handles), - str(self.output_names) - ) + return 'inputs_num: %d\ninputs_names: %s\noutputs_num: %d\noutputs_names: %s' % (len( + self.input_handles), str(self.input_names), len(self.output_handles), str(self.output_names)) # 类调用函数 def __call__(self, *input_datas, batch_size=1): @@ -59,9 +56,11 @@ class InferenceModel(): try: int(os.environ.get('CUDA_VISIBLE_DEVICES')) except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) use_gpu = False - + # 加载模型参数 if combined: model = os.path.join(modelpath, "__model__") @@ -71,7 +70,7 @@ class InferenceModel(): config = Config(modelpath) # 设置参数 - if use_gpu: + if use_gpu: config.enable_use_gpu(100, 0) else: config.disable_gpu() @@ -125,17 +124,17 @@ class InferenceModel(): self.input_handles[i].copy_from_cpu(input_data) self.predictor.run() - + for i in range(len(self.output_handles)): output = self.output_handles[i].copy_to_cpu() if i in outputs: outputs[i].append(output) else: outputs[i] = [output] - + # 预测结果合并 for key in outputs.keys(): outputs[key] = np.concatenate(outputs[key], 0) # 返回预测结果 - return outputs \ No newline at end of file + return outputs diff --git a/modules/image/depth_estimation/MiDaS_Large/module.py b/modules/thirdparty/image/depth_estimation/MiDaS_Large/module.py similarity index 83% rename from modules/image/depth_estimation/MiDaS_Large/module.py rename to modules/thirdparty/image/depth_estimation/MiDaS_Large/module.py index 3250c4198e911b144479f39a60360e2979ea3459..2b855ab8183b9aab1b6028317b3aa2492cec4367 100644 --- a/modules/image/depth_estimation/MiDaS_Large/module.py +++ b/modules/thirdparty/image/depth_estimation/MiDaS_Large/module.py @@ -26,12 +26,7 @@ class MiDaS_Large(Module): model_path = os.path.join(self.directory, "model-f6b98070") # 加载模型 - self.model = InferenceModel( - modelpath=model_path, - use_gpu=use_gpu, - use_mkldnn=False, - combined=True - ) + self.model = InferenceModel(modelpath=model_path, use_gpu=use_gpu, use_mkldnn=False, combined=True) self.model.eval() # 数据预处理配置 @@ -46,11 +41,10 @@ class MiDaS_Large(Module): resize_method="upper_bound", image_interpolation_method=cv2.INTER_CUBIC, ), - NormalizeImage(mean=[0.485, 0.456, 0.406], - std=[0.229, 0.224, 0.225]), + NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), PrepareForNet() ]) - + # 数据读取函数 @staticmethod def load_datas(paths, images): @@ -84,7 +78,7 @@ class MiDaS_Large(Module): input_data = img[np.newaxis, ...] input_datas.append(input_data) - + # 拼接数据 input_datas = np.concatenate(input_datas, 0) @@ -113,12 +107,7 @@ class MiDaS_Large(Module): return outputs # 深度估计函数 - def depth_estimation(self, - images=None, - paths=None, - batch_size=1, - output_dir='output', - visualization=False): + def depth_estimation(self, images=None, paths=None, batch_size=1, output_dir='output', visualization=False): # 加载数据 datas = self.load_datas(paths, images) @@ -130,5 +119,5 @@ class MiDaS_Large(Module): # 结果后处理 outputs = self.postprocess(datas, results, output_dir, visualization) - - return outputs \ No newline at end of file + + return outputs diff --git a/modules/image/depth_estimation/MiDaS_Small/transforms.py b/modules/thirdparty/image/depth_estimation/MiDaS_Large/transforms.py similarity index 84% rename from modules/image/depth_estimation/MiDaS_Small/transforms.py rename to modules/thirdparty/image/depth_estimation/MiDaS_Large/transforms.py index 189dfce1927695137ac2efed7d67f43a5ef5a21d..20a7c61e205707db109a48b1823b471241de8356 100644 --- a/modules/image/depth_estimation/MiDaS_Small/transforms.py +++ b/modules/thirdparty/image/depth_estimation/MiDaS_Large/transforms.py @@ -7,6 +7,7 @@ import cv2 class Resize(object): """Resize sample to given size (width, height). """ + def __init__(self, width, height, @@ -51,12 +52,10 @@ class Resize(object): y = (np.round(x / self.__multiple_of) * self.__multiple_of).astype(int) if max_val is not None and y > max_val: - y = (np.floor(x / self.__multiple_of) * - self.__multiple_of).astype(int) + y = (np.floor(x / self.__multiple_of) * self.__multiple_of).astype(int) if y < min_val: - y = (np.ceil(x / self.__multiple_of) * - self.__multiple_of).astype(int) + y = (np.ceil(x / self.__multiple_of) * self.__multiple_of).astype(int) return y @@ -91,31 +90,24 @@ class Resize(object): # fit height scale_width = scale_height else: - raise ValueError( - f"resize_method {self.__resize_method} not implemented") + raise ValueError(f"resize_method {self.__resize_method} not implemented") if self.__resize_method == "lower_bound": - new_height = self.constrain_to_multiple_of(scale_height * height, - min_val=self.__height) - new_width = self.constrain_to_multiple_of(scale_width * width, - min_val=self.__width) + new_height = self.constrain_to_multiple_of(scale_height * height, min_val=self.__height) + new_width = self.constrain_to_multiple_of(scale_width * width, min_val=self.__width) elif self.__resize_method == "upper_bound": - new_height = self.constrain_to_multiple_of(scale_height * height, - max_val=self.__height) - new_width = self.constrain_to_multiple_of(scale_width * width, - max_val=self.__width) + new_height = self.constrain_to_multiple_of(scale_height * height, max_val=self.__height) + new_width = self.constrain_to_multiple_of(scale_width * width, max_val=self.__width) elif self.__resize_method == "minimal": new_height = self.constrain_to_multiple_of(scale_height * height) new_width = self.constrain_to_multiple_of(scale_width * width) else: - raise ValueError( - f"resize_method {self.__resize_method} not implemented") + raise ValueError(f"resize_method {self.__resize_method} not implemented") return (new_width, new_height) def __call__(self, sample): - width, height = self.get_size(sample["image"].shape[1], - sample["image"].shape[0]) + width, height = self.get_size(sample["image"].shape[1], sample["image"].shape[0]) # resize sample sample["image"] = cv2.resize( @@ -133,8 +125,7 @@ class Resize(object): ) if "depth" in sample: - sample["depth"] = cv2.resize(sample["depth"], (width, height), - interpolation=cv2.INTER_NEAREST) + sample["depth"] = cv2.resize(sample["depth"], (width, height), interpolation=cv2.INTER_NEAREST) sample["mask"] = cv2.resize( sample["mask"].astype(np.float32), @@ -149,6 +140,7 @@ class Resize(object): class NormalizeImage(object): """Normlize image by given mean and std. """ + def __init__(self, mean, std): self.__mean = mean self.__std = std @@ -162,6 +154,7 @@ class NormalizeImage(object): class PrepareForNet(object): """Prepare sample for usage as network input. """ + def __init__(self): pass diff --git a/modules/image/depth_estimation/MiDaS_Large/utils.py b/modules/thirdparty/image/depth_estimation/MiDaS_Large/utils.py similarity index 86% rename from modules/image/depth_estimation/MiDaS_Large/utils.py rename to modules/thirdparty/image/depth_estimation/MiDaS_Large/utils.py index 2a45c7b62ee94783c4cdd57930c844f0854904de..139aa7b93d10e70f68cfc5982a9e670776c8249e 100644 --- a/modules/image/depth_estimation/MiDaS_Large/utils.py +++ b/modules/thirdparty/image/depth_estimation/MiDaS_Large/utils.py @@ -25,12 +25,10 @@ def write_pfm(path, image, scale=1): if len(image.shape) == 3 and image.shape[2] == 3: # color image color = True - elif (len(image.shape) == 2 - or len(image.shape) == 3 and image.shape[2] == 1): # greyscale + elif (len(image.shape) == 2 or len(image.shape) == 3 and image.shape[2] == 1): # greyscale color = False else: - raise Exception( - "Image must have H x W x 3, H x W x 1 or H x W dimensions.") + raise Exception("Image must have H x W x 3, H x W x 1 or H x W dimensions.") file.write("PF\n" if color else "Pf\n".encode()) file.write("%d %d\n".encode() % (image.shape[1], image.shape[0])) diff --git a/modules/image/depth_estimation/MiDaS_Small/README.md b/modules/thirdparty/image/depth_estimation/MiDaS_Small/README.md similarity index 100% rename from modules/image/depth_estimation/MiDaS_Small/README.md rename to modules/thirdparty/image/depth_estimation/MiDaS_Small/README.md diff --git a/modules/image/depth_estimation/MiDaS_Small/inference.py b/modules/thirdparty/image/depth_estimation/MiDaS_Small/inference.py similarity index 86% rename from modules/image/depth_estimation/MiDaS_Small/inference.py rename to modules/thirdparty/image/depth_estimation/MiDaS_Small/inference.py index 6ebe297ae4c921e07190c6375e07ecaba0d85a8c..f3a2f3c2f03dc723be6cefba5d51e83ca47bdd17 100644 --- a/modules/image/depth_estimation/MiDaS_Small/inference.py +++ b/modules/thirdparty/image/depth_estimation/MiDaS_Small/inference.py @@ -5,6 +5,7 @@ from paddle.inference import create_predictor, Config __all__ = ['InferenceModel'] + class InferenceModel(): # 初始化函数 def __init__(self, modelpath, use_gpu=False, use_mkldnn=False, combined=True): @@ -25,14 +26,10 @@ class InferenceModel(): # 打印函数 def __repr__(self): ''' - get the numbers and name of inputs and outputs + get the numbers and name of inputs and outputs ''' - return 'inputs_num: %d\ninputs_names: %s\noutputs_num: %d\noutputs_names: %s' % ( - len(self.input_handles), - str(self.input_names), - len(self.output_handles), - str(self.output_names) - ) + return 'inputs_num: %d\ninputs_names: %s\noutputs_num: %d\noutputs_names: %s' % (len( + self.input_handles), str(self.input_names), len(self.output_handles), str(self.output_names)) # 类调用函数 def __call__(self, *input_datas, batch_size=1): @@ -59,9 +56,11 @@ class InferenceModel(): try: int(os.environ.get('CUDA_VISIBLE_DEVICES')) except Exception: - print('Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.') + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) use_gpu = False - + # 加载模型参数 if combined: model = os.path.join(modelpath, "__model__") @@ -71,7 +70,7 @@ class InferenceModel(): config = Config(modelpath) # 设置参数 - if use_gpu: + if use_gpu: config.enable_use_gpu(100, 0) else: config.disable_gpu() @@ -125,17 +124,17 @@ class InferenceModel(): self.input_handles[i].copy_from_cpu(input_data) self.predictor.run() - + for i in range(len(self.output_handles)): output = self.output_handles[i].copy_to_cpu() if i in outputs: outputs[i].append(output) else: outputs[i] = [output] - + # 预测结果合并 for key in outputs.keys(): outputs[key] = np.concatenate(outputs[key], 0) # 返回预测结果 - return outputs \ No newline at end of file + return outputs diff --git a/modules/image/depth_estimation/MiDaS_Small/module.py b/modules/thirdparty/image/depth_estimation/MiDaS_Small/module.py similarity index 83% rename from modules/image/depth_estimation/MiDaS_Small/module.py rename to modules/thirdparty/image/depth_estimation/MiDaS_Small/module.py index 1abd6fe540bc981bf7b103f5769c5c746d12f7f7..041637d7c388c794081b99c00f8aa597375a5d3c 100644 --- a/modules/image/depth_estimation/MiDaS_Small/module.py +++ b/modules/thirdparty/image/depth_estimation/MiDaS_Small/module.py @@ -26,12 +26,7 @@ class MiDaS_Small(Module): model_path = os.path.join(self.directory, "model-small") # 加载模型 - self.model = InferenceModel( - modelpath=model_path, - use_gpu=use_gpu, - use_mkldnn=False, - combined=True - ) + self.model = InferenceModel(modelpath=model_path, use_gpu=use_gpu, use_mkldnn=False, combined=True) self.model.eval() # 数据预处理配置 @@ -46,11 +41,10 @@ class MiDaS_Small(Module): resize_method="upper_bound", image_interpolation_method=cv2.INTER_CUBIC, ), - NormalizeImage(mean=[0.485, 0.456, 0.406], - std=[0.229, 0.224, 0.225]), + NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), PrepareForNet() ]) - + # 数据读取函数 @staticmethod def load_datas(paths, images): @@ -84,7 +78,7 @@ class MiDaS_Small(Module): input_data = img[np.newaxis, ...] input_datas.append(input_data) - + # 拼接数据 input_datas = np.concatenate(input_datas, 0) @@ -113,12 +107,7 @@ class MiDaS_Small(Module): return outputs # 深度估计函数 - def depth_estimation(self, - images=None, - paths=None, - batch_size=1, - output_dir='output', - visualization=False): + def depth_estimation(self, images=None, paths=None, batch_size=1, output_dir='output', visualization=False): # 加载数据 datas = self.load_datas(paths, images) @@ -130,5 +119,5 @@ class MiDaS_Small(Module): # 结果后处理 outputs = self.postprocess(datas, results, output_dir, visualization) - - return outputs \ No newline at end of file + + return outputs diff --git a/modules/image/depth_estimation/MiDaS_Large/transforms.py b/modules/thirdparty/image/depth_estimation/MiDaS_Small/transforms.py similarity index 84% rename from modules/image/depth_estimation/MiDaS_Large/transforms.py rename to modules/thirdparty/image/depth_estimation/MiDaS_Small/transforms.py index 189dfce1927695137ac2efed7d67f43a5ef5a21d..20a7c61e205707db109a48b1823b471241de8356 100644 --- a/modules/image/depth_estimation/MiDaS_Large/transforms.py +++ b/modules/thirdparty/image/depth_estimation/MiDaS_Small/transforms.py @@ -7,6 +7,7 @@ import cv2 class Resize(object): """Resize sample to given size (width, height). """ + def __init__(self, width, height, @@ -51,12 +52,10 @@ class Resize(object): y = (np.round(x / self.__multiple_of) * self.__multiple_of).astype(int) if max_val is not None and y > max_val: - y = (np.floor(x / self.__multiple_of) * - self.__multiple_of).astype(int) + y = (np.floor(x / self.__multiple_of) * self.__multiple_of).astype(int) if y < min_val: - y = (np.ceil(x / self.__multiple_of) * - self.__multiple_of).astype(int) + y = (np.ceil(x / self.__multiple_of) * self.__multiple_of).astype(int) return y @@ -91,31 +90,24 @@ class Resize(object): # fit height scale_width = scale_height else: - raise ValueError( - f"resize_method {self.__resize_method} not implemented") + raise ValueError(f"resize_method {self.__resize_method} not implemented") if self.__resize_method == "lower_bound": - new_height = self.constrain_to_multiple_of(scale_height * height, - min_val=self.__height) - new_width = self.constrain_to_multiple_of(scale_width * width, - min_val=self.__width) + new_height = self.constrain_to_multiple_of(scale_height * height, min_val=self.__height) + new_width = self.constrain_to_multiple_of(scale_width * width, min_val=self.__width) elif self.__resize_method == "upper_bound": - new_height = self.constrain_to_multiple_of(scale_height * height, - max_val=self.__height) - new_width = self.constrain_to_multiple_of(scale_width * width, - max_val=self.__width) + new_height = self.constrain_to_multiple_of(scale_height * height, max_val=self.__height) + new_width = self.constrain_to_multiple_of(scale_width * width, max_val=self.__width) elif self.__resize_method == "minimal": new_height = self.constrain_to_multiple_of(scale_height * height) new_width = self.constrain_to_multiple_of(scale_width * width) else: - raise ValueError( - f"resize_method {self.__resize_method} not implemented") + raise ValueError(f"resize_method {self.__resize_method} not implemented") return (new_width, new_height) def __call__(self, sample): - width, height = self.get_size(sample["image"].shape[1], - sample["image"].shape[0]) + width, height = self.get_size(sample["image"].shape[1], sample["image"].shape[0]) # resize sample sample["image"] = cv2.resize( @@ -133,8 +125,7 @@ class Resize(object): ) if "depth" in sample: - sample["depth"] = cv2.resize(sample["depth"], (width, height), - interpolation=cv2.INTER_NEAREST) + sample["depth"] = cv2.resize(sample["depth"], (width, height), interpolation=cv2.INTER_NEAREST) sample["mask"] = cv2.resize( sample["mask"].astype(np.float32), @@ -149,6 +140,7 @@ class Resize(object): class NormalizeImage(object): """Normlize image by given mean and std. """ + def __init__(self, mean, std): self.__mean = mean self.__std = std @@ -162,6 +154,7 @@ class NormalizeImage(object): class PrepareForNet(object): """Prepare sample for usage as network input. """ + def __init__(self): pass diff --git a/modules/image/depth_estimation/MiDaS_Small/utils.py b/modules/thirdparty/image/depth_estimation/MiDaS_Small/utils.py similarity index 86% rename from modules/image/depth_estimation/MiDaS_Small/utils.py rename to modules/thirdparty/image/depth_estimation/MiDaS_Small/utils.py index 2a45c7b62ee94783c4cdd57930c844f0854904de..139aa7b93d10e70f68cfc5982a9e670776c8249e 100644 --- a/modules/image/depth_estimation/MiDaS_Small/utils.py +++ b/modules/thirdparty/image/depth_estimation/MiDaS_Small/utils.py @@ -25,12 +25,10 @@ def write_pfm(path, image, scale=1): if len(image.shape) == 3 and image.shape[2] == 3: # color image color = True - elif (len(image.shape) == 2 - or len(image.shape) == 3 and image.shape[2] == 1): # greyscale + elif (len(image.shape) == 2 or len(image.shape) == 3 and image.shape[2] == 1): # greyscale color = False else: - raise Exception( - "Image must have H x W x 3, H x W x 1 or H x W dimensions.") + raise Exception("Image must have H x W x 3, H x W x 1 or H x W dimensions.") file.write("PF\n" if color else "Pf\n".encode()) file.write("%d %d\n".encode() % (image.shape[1], image.shape[0])) diff --git a/modules/image/keypoint_detection/hand_pose_localization/README.md b/modules/thirdparty/image/keypoint_detection/hand_pose_localization/README.md similarity index 100% rename from modules/image/keypoint_detection/hand_pose_localization/README.md rename to modules/thirdparty/image/keypoint_detection/hand_pose_localization/README.md diff --git a/modules/thirdparty/image/keypoint_detection/hand_pose_localization/model.py b/modules/thirdparty/image/keypoint_detection/hand_pose_localization/model.py new file mode 100644 index 0000000000000000000000000000000000000000..ebe42971678e28e9e339cd38d7a3bf181afc121b --- /dev/null +++ b/modules/thirdparty/image/keypoint_detection/hand_pose_localization/model.py @@ -0,0 +1,76 @@ +import os +import numpy as np + +from paddle.inference import create_predictor, Config + +__all__ = ['Model'] + + +class Model(): + # 初始化函数 + def __init__(self, modelpath, use_gpu=False, use_mkldnn=True, combined=True): + # 加载模型预测器 + self.predictor = self.load_model(modelpath, use_gpu, use_mkldnn, combined) + + # 获取模型的输入输出 + self.input_names = self.predictor.get_input_names() + self.output_names = self.predictor.get_output_names() + self.input_handle = self.predictor.get_input_handle(self.input_names[0]) + self.output_handle = self.predictor.get_output_handle(self.output_names[0]) + + # 模型加载函数 + def load_model(self, modelpath, use_gpu, use_mkldnn, combined): + # 对运行位置进行配置 + if use_gpu: + try: + int(os.environ.get('CUDA_VISIBLE_DEVICES')) + except Exception: + print( + 'Error! Unable to use GPU. Please set the environment variables "CUDA_VISIBLE_DEVICES=GPU_id" to use GPU.' + ) + use_gpu = False + + # 加载模型参数 + if combined: + model = os.path.join(modelpath, "__model__") + params = os.path.join(modelpath, "__params__") + config = Config(model, params) + else: + config = Config(modelpath) + + # 设置参数 + if use_gpu: + config.enable_use_gpu(100, 0) + else: + config.disable_gpu() + if use_mkldnn: + config.enable_mkldnn() + config.disable_glog_info() + config.switch_ir_optim(True) + config.enable_memory_optim() + config.switch_use_feed_fetch_ops(False) + config.switch_specify_input_names(True) + + # 通过参数加载模型预测器 + predictor = create_predictor(config) + + # 返回预测器 + return predictor + + # 模型预测函数 + def predict(self, input_datas): + outputs = [] + + # 遍历输入数据进行预测 + for input_data in input_datas: + inputs = input_data.copy() + self.input_handle.copy_from_cpu(inputs) + self.predictor.run() + output = self.output_handle.copy_to_cpu() + outputs.append(output) + + # 预测结果合并 + outputs = np.concatenate(outputs, 0) + + # 返回预测结果 + return outputs diff --git a/modules/image/keypoint_detection/hand_pose_localization/module.py b/modules/thirdparty/image/keypoint_detection/hand_pose_localization/module.py similarity index 100% rename from modules/image/keypoint_detection/hand_pose_localization/module.py rename to modules/thirdparty/image/keypoint_detection/hand_pose_localization/module.py diff --git a/modules/image/keypoint_detection/hand_pose_localization/processor.py b/modules/thirdparty/image/keypoint_detection/hand_pose_localization/processor.py similarity index 100% rename from modules/image/keypoint_detection/hand_pose_localization/processor.py rename to modules/thirdparty/image/keypoint_detection/hand_pose_localization/processor.py diff --git a/hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/Readme.md b/modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/Readme.md similarity index 100% rename from hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/Readme.md rename to modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/Readme.md diff --git a/modules/text/text_generation/reading_pictures_writing_poems/__init__.py b/modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/__init__.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems/__init__.py rename to modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/__init__.py diff --git a/hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/function.py b/modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/function.py similarity index 96% rename from hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/function.py rename to modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/function.py index c810de705254b2ca375ff11ccc21d65d4226eb25..bb83b2237b9bcff8cfdb730175bb2e4250868123 100644 --- a/hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/function.py +++ b/modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/function.py @@ -2,10 +2,11 @@ import numpy as np import cv2 from scipy import ndimage + def get_normal_map(img): img = img.astype(np.float) img = img / 255.0 - img = - img + 1 + img = -img + 1 img[img < 0] = 0 img[img > 1] = 1 return img @@ -112,7 +113,7 @@ def resize_img_512(img): def resize_img_512_3d(img): zeros = np.zeros((1, 3, 512, 512), dtype=np.float) - zeros[0, 0: img.shape[0], 0: img.shape[1], 0: img.shape[2]] = img + zeros[0, 0:img.shape[0], 0:img.shape[1], 0:img.shape[2]] = img return zeros.transpose((1, 2, 3, 0)) @@ -122,7 +123,7 @@ def denoise_mat(img, i): def show_active_img_and_save_denoise(img, path): mat = img.astype(np.float) - mat = - mat + 1 + mat = -mat + 1 mat = mat * 255.0 mat[mat < 0] = 0 mat[mat > 255] = 255 @@ -132,11 +133,9 @@ def show_active_img_and_save_denoise(img, path): return - - def show_active_img(name, img): mat = img.astype(np.float) - mat = - mat + 1 + mat = -mat + 1 mat = mat * 255.0 mat[mat < 0] = 0 mat[mat > 255] = 255 @@ -147,7 +146,7 @@ def show_active_img(name, img): def get_active_img(img): mat = img.astype(np.float) - mat = - mat + 1 + mat = -mat + 1 mat = mat * 255.0 mat[mat < 0] = 0 mat[mat > 255] = 255 @@ -158,7 +157,7 @@ def get_active_img(img): def get_active_img_fil(img): mat = img.astype(np.float) mat[mat < 0.18] = 0 - mat = - mat + 1 + mat = -mat + 1 mat = mat * 255.0 mat[mat < 0] = 0 mat[mat > 255] = 255 diff --git a/hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/module.py b/modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/module.py similarity index 89% rename from hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/module.py rename to modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/module.py index fab38574686744ad0e8d5c3c11cc9166ce2a73c4..f1aa37769f14281a9d1e4e99980c76494aa81af9 100644 --- a/hub_module/modules/image/semantic_segmentation/Extract_Line_Draft/module.py +++ b/modules/thirdparty/image/semantic_segmentation/Extract_Line_Draft/module.py @@ -14,12 +14,12 @@ import paddle.fluid as fluid import paddlehub as hub from Extract_Line_Draft.function import * + @moduleinfo( name="Extract_Line_Draft", version="1.0.0", type="cv/segmentation", - summary= - "Import the color picture and generate the line draft of the picture", + summary="Import the color picture and generate the line draft of the picture", author="彭兆帅，郑博培", author_email="1084667371@qq.com，2733821739@qq.com") class ExtractLineDraft(hub.Module): @@ -28,9 +28,10 @@ class ExtractLineDraft(hub.Module): Initialize with the necessary elements """ # 加载模型路径 - self.default_pretrained_model_path = os.path.join(self.directory, "assets","infer_model") + self.default_pretrained_model_path = os.path.join(self.directory, "assets", "infer_model") self._set_config() - def _set_config(self): + + def _set_config(self): """ predictor config setting """ @@ -72,7 +73,7 @@ class ExtractLineDraft(hub.Module): self.predictor.zero_copy_run() output = self.output_tensor.copy_to_cpu() outputs.append(output) - + # 预测结果合并 outputs = np.concatenate(outputs, 0) @@ -153,12 +154,9 @@ class ExtractLineDraft(hub.Module): usage='%(prog)s', add_help=True) - self.arg_input_group = self.parser.add_argument_group( - title="Input options", description="Input data. Required") + self.arg_input_group = self.parser.add_argument_group(title="Input options", description="Input data. Required") self.arg_config_group = self.parser.add_argument_group( - title="Config options", - description= - "Run configuration for controlling module behavior, not required.") + title="Config options", description="Run configuration for controlling module behavior, not required.") self.add_module_input_arg() @@ -173,21 +171,12 @@ class ExtractLineDraft(hub.Module): use_gpu = args.use_gpu self.ExtractLine(image=input_data, use_gpu=use_gpu) - def add_module_input_arg(self): """ Add the command input options """ - self.arg_input_group.add_argument( - '--image', - type=str, - default=None, - help="file contain input data") - self.arg_input_group.add_argument( - '--use_gpu', - type=ast.literal_eval, - default=None, - help="weather to use gpu") + self.arg_input_group.add_argument('--image', type=str, default=None, help="file contain input data") + self.arg_input_group.add_argument('--use_gpu', type=ast.literal_eval, default=None, help="weather to use gpu") def check_input_data(self, args): input_data = [] @@ -196,4 +185,3 @@ class ExtractLineDraft(hub.Module): raise RuntimeError("Path %s is not exist." % args.image) path = "{}".format(args.image) return path - diff --git a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/README.md b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/README.md similarity index 100% rename from modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/README.md rename to modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/README.md diff --git a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/__init__.py b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/__init__.py similarity index 100% rename from modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/__init__.py rename to modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/__init__.py diff --git a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/fcn.py b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/fcn.py similarity index 79% rename from modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/fcn.py rename to modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/fcn.py index c2af584c0765ecf83976867834b8d406340dde37..2063c63086c4e4f9b7b57269c9cc5a6f3fc9078f 100644 --- a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/fcn.py +++ b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/fcn.py @@ -48,12 +48,9 @@ class FCN(nn.Layer): super(FCN, self).__init__() self.backbone = backbone - backbone_channels = [ - backbone.feat_channels[i] for i in backbone_indices - ] + backbone_channels = [backbone.feat_channels[i] for i in backbone_indices] - self.head = FCNHead(num_classes, backbone_indices, backbone_channels, - channels) + self.head = FCNHead(num_classes, backbone_indices, backbone_channels, channels) self.align_corners = align_corners self.pretrained = pretrained @@ -62,11 +59,7 @@ class FCN(nn.Layer): feat_list = self.backbone(x) logit_list = self.head(feat_list) return [ - F.interpolate( - logit, - x.shape[2:], - mode='bilinear', - align_corners=self.align_corners) for logit in logit_list + F.interpolate(logit, x.shape[2:], mode='bilinear', align_corners=self.align_corners) for logit in logit_list ] @@ -83,11 +76,7 @@ class FCNHead(nn.Layer): pretrained (str, optional): The path of pretrained model. Default: None """ - def __init__(self, - num_classes, - backbone_indices=(-1, ), - backbone_channels=(270, ), - channels=None): + def __init__(self, num_classes, backbone_indices=(-1, ), backbone_channels=(270, ), channels=None): super(FCNHead, self).__init__() self.num_classes = num_classes @@ -96,17 +85,8 @@ class FCNHead(nn.Layer): channels = backbone_channels[0] self.conv_1 = ConvBNReLU( - in_channels=backbone_channels[0], - out_channels=channels, - kernel_size=1, - padding='same', - stride=1) - self.cls = nn.Conv2D( - in_channels=channels, - out_channels=self.num_classes, - kernel_size=1, - stride=1, - padding=0) + in_channels=backbone_channels[0], out_channels=channels, kernel_size=1, padding='same', stride=1) + self.cls = nn.Conv2D(in_channels=channels, out_channels=self.num_classes, kernel_size=1, stride=1, padding=0) def forward(self, feat_list): logit_list = [] @@ -115,4 +95,3 @@ class FCNHead(nn.Layer): logit = self.cls(x) logit_list.append(logit) return logit_list - diff --git a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/hrnet.py b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/hrnet.py similarity index 83% rename from modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/hrnet.py rename to modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/hrnet.py index 9973b1ad2cd32e4c8706825ac9ca8272d32c07a6..e4b88a02819b6790827dd37e872e56484caab9d1 100644 --- a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/hrnet.py +++ b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/hrnet.py @@ -21,8 +21,8 @@ import paddle.nn.functional as F from .layers import ConvBNReLU, ConvBN __all__ = [ - "HRNet_W18_Small_V1", "HRNet_W18_Small_V2", "HRNet_W18", "HRNet_W30", - "HRNet_W32", "HRNet_W40", "HRNet_W44", "HRNet_W48", "HRNet_W60", "HRNet_W64" + "HRNet_W18_Small_V1", "HRNet_W18_Small_V2", "HRNet_W18", "HRNet_W30", "HRNet_W32", "HRNet_W40", "HRNet_W44", + "HRNet_W48", "HRNet_W60", "HRNet_W64" ] @@ -88,20 +88,10 @@ class HRNet(nn.Layer): self.feat_channels = [sum(stage4_num_channels)] self.conv_layer1_1 = ConvBNReLU( - in_channels=3, - out_channels=64, - kernel_size=3, - stride=2, - padding='same', - bias_attr=False) + in_channels=3, out_channels=64, kernel_size=3, stride=2, padding='same', bias_attr=False) self.conv_layer1_2 = ConvBNReLU( - in_channels=64, - out_channels=64, - kernel_size=3, - stride=2, - padding='same', - bias_attr=False) + in_channels=64, out_channels=64, kernel_size=3, stride=2, padding='same', bias_attr=False) self.la1 = Layer1( num_channels=64, @@ -111,9 +101,7 @@ class HRNet(nn.Layer): name="layer2") self.tr1 = TransitionLayer( - in_channels=[self.stage1_num_channels[0] * 4], - out_channels=self.stage2_num_channels, - name="tr1") + in_channels=[self.stage1_num_channels[0] * 4], out_channels=self.stage2_num_channels, name="tr1") self.st2 = Stage( num_channels=self.stage2_num_channels, @@ -125,9 +113,7 @@ class HRNet(nn.Layer): align_corners=align_corners) self.tr2 = TransitionLayer( - in_channels=self.stage2_num_channels, - out_channels=self.stage3_num_channels, - name="tr2") + in_channels=self.stage2_num_channels, out_channels=self.stage3_num_channels, name="tr2") self.st3 = Stage( num_channels=self.stage3_num_channels, num_modules=self.stage3_num_modules, @@ -138,9 +124,7 @@ class HRNet(nn.Layer): align_corners=align_corners) self.tr3 = TransitionLayer( - in_channels=self.stage3_num_channels, - out_channels=self.stage4_num_channels, - name="tr3") + in_channels=self.stage3_num_channels, out_channels=self.stage4_num_channels, name="tr3") self.st4 = Stage( num_channels=self.stage4_num_channels, num_modules=self.stage4_num_modules, @@ -166,30 +150,16 @@ class HRNet(nn.Layer): st4 = self.st4(tr3) x0_h, x0_w = st4[0].shape[2:] - x1 = F.interpolate( - st4[1], (x0_h, x0_w), - mode='bilinear', - align_corners=self.align_corners) - x2 = F.interpolate( - st4[2], (x0_h, x0_w), - mode='bilinear', - align_corners=self.align_corners) - x3 = F.interpolate( - st4[3], (x0_h, x0_w), - mode='bilinear', - align_corners=self.align_corners) + x1 = F.interpolate(st4[1], (x0_h, x0_w), mode='bilinear', align_corners=self.align_corners) + x2 = F.interpolate(st4[2], (x0_h, x0_w), mode='bilinear', align_corners=self.align_corners) + x3 = F.interpolate(st4[3], (x0_h, x0_w), mode='bilinear', align_corners=self.align_corners) x = paddle.concat([st4[0], x1, x2, x3], axis=1) return [x] class Layer1(nn.Layer): - def __init__(self, - num_channels, - num_filters, - num_blocks, - has_se=False, - name=None): + def __init__(self, num_channels, num_filters, num_blocks, has_se=False, name=None): super(Layer1, self).__init__() self.bottleneck_block_list = [] @@ -258,12 +228,7 @@ class TransitionLayer(nn.Layer): class Branches(nn.Layer): - def __init__(self, - num_blocks, - in_channels, - out_channels, - has_se=False, - name=None): + def __init__(self, num_blocks, in_channels, out_channels, has_se=False, name=None): super(Branches, self).__init__() self.basic_block_list = [] @@ -278,8 +243,7 @@ class Branches(nn.Layer): num_channels=in_ch, num_filters=out_channels[i], has_se=has_se, - name=name + '_branch_layer_' + str(i + 1) + '_' + - str(j + 1))) + name=name + '_branch_layer_' + str(i + 1) + '_' + str(j + 1))) self.basic_block_list[i].append(basic_block_func) def forward(self, x): @@ -293,24 +257,14 @@ class Branches(nn.Layer): class BottleneckBlock(nn.Layer): - def __init__(self, - num_channels, - num_filters, - has_se, - stride=1, - downsample=False, - name=None): + def __init__(self, num_channels, num_filters, has_se, stride=1, downsample=False, name=None): super(BottleneckBlock, self).__init__() self.has_se = has_se self.downsample = downsample self.conv1 = ConvBNReLU( - in_channels=num_channels, - out_channels=num_filters, - kernel_size=1, - padding='same', - bias_attr=False) + in_channels=num_channels, out_channels=num_filters, kernel_size=1, padding='same', bias_attr=False) self.conv2 = ConvBNReLU( in_channels=num_filters, @@ -321,26 +275,15 @@ class BottleneckBlock(nn.Layer): bias_attr=False) self.conv3 = ConvBN( - in_channels=num_filters, - out_channels=num_filters * 4, - kernel_size=1, - padding='same', - bias_attr=False) + in_channels=num_filters, out_channels=num_filters * 4, kernel_size=1, padding='same', bias_attr=False) if self.downsample: self.conv_down = ConvBN( - in_channels=num_channels, - out_channels=num_filters * 4, - kernel_size=1, - padding='same', - bias_attr=False) + in_channels=num_channels, out_channels=num_filters * 4, kernel_size=1, padding='same', bias_attr=False) if self.has_se: self.se = SELayer( - num_channels=num_filters * 4, - num_filters=num_filters * 4, - reduction_ratio=16, - name=name + '_fc') + num_channels=num_filters * 4, num_filters=num_filters * 4, reduction_ratio=16, name=name + '_fc') def forward(self, x): residual = x @@ -360,13 +303,7 @@ class BottleneckBlock(nn.Layer): class BasicBlock(nn.Layer): - def __init__(self, - num_channels, - num_filters, - stride=1, - has_se=False, - downsample=False, - name=None): + def __init__(self, num_channels, num_filters, stride=1, has_se=False, downsample=False, name=None): super(BasicBlock, self).__init__() self.has_se = has_se @@ -380,26 +317,14 @@ class BasicBlock(nn.Layer): padding='same', bias_attr=False) self.conv2 = ConvBN( - in_channels=num_filters, - out_channels=num_filters, - kernel_size=3, - padding='same', - bias_attr=False) + in_channels=num_filters, out_channels=num_filters, kernel_size=3, padding='same', bias_attr=False) if self.downsample: self.conv_down = ConvBNReLU( - in_channels=num_channels, - out_channels=num_filters, - kernel_size=1, - padding='same', - bias_attr=False) + in_channels=num_channels, out_channels=num_filters, kernel_size=1, padding='same', bias_attr=False) if self.has_se: - self.se = SELayer( - num_channels=num_filters, - num_filters=num_filters, - reduction_ratio=16, - name=name + '_fc') + self.se = SELayer(num_channels=num_filters, num_filters=num_filters, reduction_ratio=16, name=name + '_fc') def forward(self, x): residual = x @@ -428,17 +353,11 @@ class SELayer(nn.Layer): med_ch = int(num_channels / reduction_ratio) stdv = 1.0 / math.sqrt(num_channels * 1.0) self.squeeze = nn.Linear( - num_channels, - med_ch, - weight_attr=paddle.ParamAttr( - initializer=nn.initializer.Uniform(-stdv, stdv))) + num_channels, med_ch, weight_attr=paddle.ParamAttr(initializer=nn.initializer.Uniform(-stdv, stdv))) stdv = 1.0 / math.sqrt(med_ch * 1.0) self.excitation = nn.Linear( - med_ch, - num_filters, - weight_attr=paddle.ParamAttr( - initializer=nn.initializer.Uniform(-stdv, stdv))) + med_ch, num_filters, weight_attr=paddle.ParamAttr(initializer=nn.initializer.Uniform(-stdv, stdv))) def forward(self, x): pool = self.pool2d_gap(x) @@ -447,8 +366,7 @@ class SELayer(nn.Layer): squeeze = F.relu(squeeze) excitation = self.excitation(squeeze) excitation = F.sigmoid(excitation) - excitation = paddle.reshape( - excitation, shape=[-1, self._num_channels, 1, 1]) + excitation = paddle.reshape(excitation, shape=[-1, self._num_channels, 1, 1]) out = x * excitation return out @@ -512,11 +430,7 @@ class HighResolutionModule(nn.Layer): super(HighResolutionModule, self).__init__() self.branches_func = Branches( - num_blocks=num_blocks, - in_channels=num_channels, - out_channels=num_filters, - has_se=has_se, - name=name) + num_blocks=num_blocks, in_channels=num_channels, out_channels=num_filters, has_se=has_se, name=name) self.fuse_func = FuseLayers( in_channels=num_filters, @@ -532,12 +446,7 @@ class HighResolutionModule(nn.Layer): class FuseLayers(nn.Layer): - def __init__(self, - in_channels, - out_channels, - multi_scale_output=True, - name=None, - align_corners=False): + def __init__(self, in_channels, out_channels, multi_scale_output=True, name=None, align_corners=False): super(FuseLayers, self).__init__() self._actual_ch = len(in_channels) if multi_scale_output else 1 @@ -562,8 +471,7 @@ class FuseLayers(nn.Layer): for k in range(i - j): if k == i - j - 1: residual_func = self.add_sublayer( - "residual_{}_layer_{}_{}_{}".format( - name, i + 1, j + 1, k + 1), + "residual_{}_layer_{}_{}_{}".format(name, i + 1, j + 1, k + 1), ConvBN( in_channels=pre_num_filters, out_channels=out_channels[i], @@ -574,8 +482,7 @@ class FuseLayers(nn.Layer): pre_num_filters = out_channels[i] else: residual_func = self.add_sublayer( - "residual_{}_layer_{}_{}_{}".format( - name, i + 1, j + 1, k + 1), + "residual_{}_layer_{}_{}_{}".format(name, i + 1, j + 1, k + 1), ConvBNReLU( in_channels=pre_num_filters, out_channels=out_channels[j], @@ -597,11 +504,7 @@ class FuseLayers(nn.Layer): y = self.residual_func_list[residual_func_idx](x[j]) residual_func_idx += 1 - y = F.interpolate( - y, - residual_shape, - mode='bilinear', - align_corners=self.align_corners) + y = F.interpolate(y, residual_shape, mode='bilinear', align_corners=self.align_corners) residual = residual + y elif j < i: y = x[j] diff --git a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/layers.py b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/layers.py similarity index 70% rename from modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/layers.py rename to modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/layers.py index be83f19f68dfa9d49d29a510e1ef232c668c235e..cd7fcc03319369082b43525a04aa16a143052e8d 100644 --- a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/layers.py +++ b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/model/layers.py @@ -26,16 +26,10 @@ def SyncBatchNorm(*args, **kwargs): class ConvBNReLU(nn.Layer): - def __init__(self, - in_channels, - out_channels, - kernel_size, - padding='same', - **kwargs): + def __init__(self, in_channels, out_channels, kernel_size, padding='same', **kwargs): super().__init__() - self._conv = nn.Conv2D( - in_channels, out_channels, kernel_size, padding=padding, **kwargs) + self._conv = nn.Conv2D(in_channels, out_channels, kernel_size, padding=padding, **kwargs) self._batch_norm = SyncBatchNorm(out_channels) @@ -47,19 +41,12 @@ class ConvBNReLU(nn.Layer): class ConvBN(nn.Layer): - def __init__(self, - in_channels, - out_channels, - kernel_size, - padding='same', - **kwargs): + def __init__(self, in_channels, out_channels, kernel_size, padding='same', **kwargs): super().__init__() - self._conv = nn.Conv2D( - in_channels, out_channels, kernel_size, padding=padding, **kwargs) + self._conv = nn.Conv2D(in_channels, out_channels, kernel_size, padding=padding, **kwargs) self._batch_norm = SyncBatchNorm(out_channels) def forward(self, x): x = self._conv(x) x = self._batch_norm(x) return x - diff --git a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/module.py b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/module.py similarity index 78% rename from modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/module.py rename to modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/module.py index ffe691a4cfd914babeb91a3334fbbe99cb15c103..92e5616b477a50932e312f543be4ce3e0fcbf10f 100644 --- a/modules/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/module.py +++ b/modules/thirdparty/image/semantic_segmentation/FCN_HRNet_W18_Face_Seg/module.py @@ -6,13 +6,14 @@ import numpy as np from FCN_HRNet_W18_Face_Seg.model import FCN, HRNet_W18 from paddlehub.module.module import moduleinfo + @moduleinfo( - name="FCN_HRNet_W18_Face_Seg", # 模型名称 - type="CV", # 模型类型 - author="jm12138", # 作者名称 - author_email="jm12138@qq.com", # 作者邮箱 - summary="FCN_HRNet_W18_Face_Seg", # 模型介绍 - version="1.0.0" # 版本号 + name="FCN_HRNet_W18_Face_Seg", # 模型名称 + type="CV", # 模型类型 + author="jm12138", # 作者名称 + author_email="jm12138@qq.com", # 作者邮箱 + summary="FCN_HRNet_W18_Face_Seg", # 模型介绍 + version="1.0.0" # 版本号 ) class FCN_HRNet_W18_Face_Seg(nn.Layer): def __init__(self): @@ -41,10 +42,10 @@ class FCN_HRNet_W18_Face_Seg(nn.Layer): if images is not None: datas = images - + # 返回数据列表 return datas - + # 数据预处理函数 @staticmethod def preprocess(images, batch_size): @@ -64,19 +65,18 @@ class FCN_HRNet_W18_Face_Seg(nn.Layer): # 数据切分 datas_num = input_datas.shape[0] - split_num = datas_num//batch_size+1 if datas_num%batch_size!=0 else datas_num//batch_size + split_num = datas_num // batch_size + 1 if datas_num % batch_size != 0 else datas_num // batch_size input_datas = np.array_split(input_datas, split_num) return input_datas - # 结果归一化函数 @staticmethod def normPRED(d): ma = np.max(d) mi = np.min(d) - dn = (d-mi)/(ma-mi) + dn = (d - mi) / (ma - mi) return dn @@ -86,7 +86,7 @@ class FCN_HRNet_W18_Face_Seg(nn.Layer): if visualization: if not os.path.exists(output_dir): os.mkdir(output_dir) - + results = [] for output, image, i in zip(outputs, datas, range(len(datas))): @@ -96,24 +96,21 @@ class FCN_HRNet_W18_Face_Seg(nn.Layer): # 图像缩放 h, w = image.shape[:2] mask = cv2.resize(pred, (w, h)) - mask[mask<0.5] = 0. - mask[mask>0.55] = 1. - + mask[mask < 0.5] = 0. + mask[mask > 0.55] = 1. + # 计算输出图像 face = (image * mask[..., np.newaxis] + (1 - mask[..., np.newaxis]) * 255).astype(np.uint8) # 格式还原 mask = (mask * 255).astype(np.uint8) - + # 可视化结果保存 if visualization: cv2.imwrite(os.path.join(output_dir, 'result_mask_%d.png' % i), mask) cv2.imwrite(os.path.join(output_dir, 'result_%d.png' % i), face) - results.append({ - 'mask': mask, - 'face': face - }) + results.append({'mask': mask, 'face': face}) return results @@ -132,25 +129,19 @@ class FCN_HRNet_W18_Face_Seg(nn.Layer): outputs = np.concatenate(outputs, 0) - return outputs + return outputs - def Segmentation( - self, - images=None, - paths=None, - batch_size=1, - output_dir='output', - visualization=False): + def Segmentation(self, images=None, paths=None, batch_size=1, output_dir='output', visualization=False): # 获取输入数据 datas = self.load_datas(paths, images) # 数据预处理 input_datas = self.preprocess(datas, batch_size) - + # 模型预测 outputs = self.predict(input_datas) # 结果后处理 results = self.postprocess(outputs, datas, output_dir, visualization) - return results \ No newline at end of file + return results diff --git a/modules/image/semantic_segmentation/U2Net/README.md b/modules/thirdparty/image/semantic_segmentation/U2Net/README.md similarity index 100% rename from modules/image/semantic_segmentation/U2Net/README.md rename to modules/thirdparty/image/semantic_segmentation/U2Net/README.md diff --git a/modules/image/semantic_segmentation/U2Net/module.py b/modules/thirdparty/image/semantic_segmentation/U2Net/module.py similarity index 62% rename from modules/image/semantic_segmentation/U2Net/module.py rename to modules/thirdparty/image/semantic_segmentation/U2Net/module.py index 6a7adbda0983181b7ae513f4a30ae4ce6c038c1f..964615a6246636e73a26340f94a378b3244ac8a0 100644 --- a/modules/image/semantic_segmentation/U2Net/module.py +++ b/modules/thirdparty/image/semantic_segmentation/U2Net/module.py @@ -6,18 +6,19 @@ from U2Net.u2net import U2NET from U2Net.processor import Processor from paddlehub.module.module import moduleinfo + @moduleinfo( - name="U2Net", # 模型名称 - type="CV", # 模型类型 - author="jm12138", # 作者名称 - author_email="jm12138@qq.com", # 作者邮箱 - summary="U2Net", # 模型介绍 - version="1.0.0" # 版本号 + name="U2Net", # 模型名称 + type="CV", # 模型类型 + author="jm12138", # 作者名称 + author_email="jm12138@qq.com", # 作者邮箱 + summary="U2Net", # 模型介绍 + version="1.0.0" # 版本号 ) class U2Net(nn.Layer): def __init__(self): super(U2Net, self).__init__() - self.model = U2NET(3,1) + self.model = U2NET(3, 1) state_dict = paddle.load(os.path.join(self.directory, 'u2net.pdparams')) self.model.set_dict(state_dict) self.model.eval() @@ -26,21 +27,20 @@ class U2Net(nn.Layer): outputs = [] for data in input_datas: data = paddle.to_tensor(data, 'float32') - d1,d2,d3,d4,d5,d6,d7= self.model(data) + d1, d2, d3, d4, d5, d6, d7 = self.model(data) outputs.append(d1.numpy()) outputs = np.concatenate(outputs, 0) - + return outputs - def Segmentation( - self, - images=None, - paths=None, - batch_size=1, - input_size=320, - output_dir='output', - visualization=False): + def Segmentation(self, + images=None, + paths=None, + batch_size=1, + input_size=320, + output_dir='output', + visualization=False): # 初始化数据处理器 processor = Processor(paths, images, batch_size, input_size) diff --git a/modules/image/semantic_segmentation/U2Net/processor.py b/modules/thirdparty/image/semantic_segmentation/U2Net/processor.py similarity index 69% rename from modules/image/semantic_segmentation/U2Net/processor.py rename to modules/thirdparty/image/semantic_segmentation/U2Net/processor.py index a6cef1ae1a98c95e2170e2b6842d76c481e5cb0c..949f119e7990c9453d84587c0109e27a61271744 100644 --- a/modules/image/semantic_segmentation/U2Net/processor.py +++ b/modules/thirdparty/image/semantic_segmentation/U2Net/processor.py @@ -4,6 +4,7 @@ import numpy as np __all__ = ['Processor'] + class Processor(): def __init__(self, paths, images, batch_size, input_size): # 图像列表 @@ -25,7 +26,7 @@ class Processor(): if images is not None: datas = images - + # 返回数据列表 return datas @@ -34,22 +35,22 @@ class Processor(): input_datas = [] for image in imgs: image = cv2.resize(image, (input_size, input_size)) - tmpImg = np.zeros((image.shape[0],image.shape[1],3)) - image = image/np.max(image) + tmpImg = np.zeros((image.shape[0], image.shape[1], 3)) + image = image / np.max(image) - tmpImg[:,:,0] = (image[:,:,0]-0.485)/0.229 - tmpImg[:,:,1] = (image[:,:,1]-0.456)/0.224 - tmpImg[:,:,2] = (image[:,:,2]-0.406)/0.225 + tmpImg[:, :, 0] = (image[:, :, 0] - 0.485) / 0.229 + tmpImg[:, :, 1] = (image[:, :, 1] - 0.456) / 0.224 + tmpImg[:, :, 2] = (image[:, :, 2] - 0.406) / 0.225 # convert BGR to RGB tmpImg = tmpImg.transpose((2, 0, 1)) - tmpImg = tmpImg[np.newaxis,:,:,:] + tmpImg = tmpImg[np.newaxis, :, :, :] input_datas.append(tmpImg) - + input_datas = np.concatenate(input_datas, 0) datas_num = input_datas.shape[0] - split_num = datas_num//batch_size+1 if datas_num%batch_size!=0 else datas_num//batch_size + split_num = datas_num // batch_size + 1 if datas_num % batch_size != 0 else datas_num // batch_size input_datas = np.array_split(input_datas, split_num) @@ -59,7 +60,7 @@ class Processor(): ma = np.max(d) mi = np.min(d) - dn = (d-mi)/(ma-mi) + dn = (d - mi) / (ma - mi) return dn @@ -68,10 +69,10 @@ class Processor(): results = [] if visualization and not os.path.exists(output_dir): os.mkdir(output_dir) - + for i, image in enumerate(self.imgs): # normalization - pred = outputs[i,0,:,:] + pred = outputs[i, 0, :, :] pred = self.normPRED(pred) @@ -79,17 +80,14 @@ class Processor(): h, w = image.shape[:2] mask = cv2.resize(pred, (w, h)) - output_img = (image*mask[..., np.newaxis] + (1-mask[..., np.newaxis])*255).astype(np.uint8) + output_img = (image * mask[..., np.newaxis] + (1 - mask[..., np.newaxis]) * 255).astype(np.uint8) + + mask = (mask * 255).astype(np.uint8) - mask = (mask*255).astype(np.uint8) - if visualization: cv2.imwrite(os.path.join(output_dir, 'result_mask_%d.png' % i), mask) cv2.imwrite(os.path.join(output_dir, 'result_%d.png' % i), output_img) - results.append({ - 'mask': mask, - 'front': output_img - }) - - return results \ No newline at end of file + results.append({'mask': mask, 'front': output_img}) + + return results diff --git a/modules/thirdparty/image/semantic_segmentation/U2Net/u2net.py b/modules/thirdparty/image/semantic_segmentation/U2Net/u2net.py new file mode 100644 index 0000000000000000000000000000000000000000..3a7ecd0e90d4386df33f532833ceca48fc0d62a0 --- /dev/null +++ b/modules/thirdparty/image/semantic_segmentation/U2Net/u2net.py @@ -0,0 +1,524 @@ +import paddle +import paddle.nn as nn +import paddle.nn.functional as F + +__all__ = ['U2NETP', 'U2NET'] + + +class REBNCONV(nn.Layer): + def __init__(self, in_ch=3, out_ch=3, dirate=1): + super(REBNCONV, self).__init__() + + self.conv_s1 = nn.Conv2D(in_ch, out_ch, 3, padding=1 * dirate, dilation=1 * dirate) + self.bn_s1 = nn.BatchNorm2D(out_ch) + self.relu_s1 = nn.ReLU() + + def forward(self, x): + + hx = x + xout = self.relu_s1(self.bn_s1(self.conv_s1(hx))) + + return xout + + +## upsample tensor 'src' to have the same spatial size with tensor 'tar' +def _upsample_like(src, tar): + + src = F.upsample(src, size=tar.shape[2:], mode='bilinear') + + return src + + +### RSU-7 ### +class RSU7(nn.Layer): #UNet07DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU7, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool4 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool5 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv7 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv6d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + hx = self.pool4(hx4) + + hx5 = self.rebnconv5(hx) + hx = self.pool5(hx5) + + hx6 = self.rebnconv6(hx) + + hx7 = self.rebnconv7(hx6) + + hx6d = self.rebnconv6d(paddle.concat((hx7, hx6), 1)) + hx6dup = _upsample_like(hx6d, hx5) + + hx5d = self.rebnconv5d(paddle.concat((hx6dup, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-6 ### +class RSU6(nn.Layer): #UNet06DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU6, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool4 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + hx = self.pool4(hx4) + + hx5 = self.rebnconv5(hx) + + hx6 = self.rebnconv6(hx5) + + hx5d = self.rebnconv5d(paddle.concat((hx6, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-5 ### +class RSU5(nn.Layer): #UNet05DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU5, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + + hx5 = self.rebnconv5(hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-4 ### +class RSU4(nn.Layer): #UNet04DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU4, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + + hx4 = self.rebnconv4(hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-4F ### +class RSU4F(nn.Layer): #UNet04FRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU4F, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=2) + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=4) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=8) + + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=4) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=2) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx2 = self.rebnconv2(hx1) + hx3 = self.rebnconv3(hx2) + + hx4 = self.rebnconv4(hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4, hx3), 1)) + hx2d = self.rebnconv2d(paddle.concat((hx3d, hx2), 1)) + hx1d = self.rebnconv1d(paddle.concat((hx2d, hx1), 1)) + + return hx1d + hxin + + +##### U^2-Net #### +class U2NET(nn.Layer): + def __init__(self, in_ch=3, out_ch=1): + super(U2NET, self).__init__() + + self.stage1 = RSU7(in_ch, 32, 64) + self.pool12 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage2 = RSU6(64, 32, 128) + self.pool23 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage3 = RSU5(128, 64, 256) + self.pool34 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage4 = RSU4(256, 128, 512) + self.pool45 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage5 = RSU4F(512, 256, 512) + self.pool56 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage6 = RSU4F(512, 256, 512) + + # decoder + self.stage5d = RSU4F(1024, 256, 512) + self.stage4d = RSU4(1024, 128, 256) + self.stage3d = RSU5(512, 64, 128) + self.stage2d = RSU6(256, 32, 64) + self.stage1d = RSU7(128, 16, 64) + + self.side1 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side2 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side3 = nn.Conv2D(128, out_ch, 3, padding=1) + self.side4 = nn.Conv2D(256, out_ch, 3, padding=1) + self.side5 = nn.Conv2D(512, out_ch, 3, padding=1) + self.side6 = nn.Conv2D(512, out_ch, 3, padding=1) + + self.outconv = nn.Conv2D(6, out_ch, 1) + + def forward(self, x): + + hx = x + + #stage 1 + hx1 = self.stage1(hx) + hx = self.pool12(hx1) + + #stage 2 + hx2 = self.stage2(hx) + hx = self.pool23(hx2) + + #stage 3 + hx3 = self.stage3(hx) + hx = self.pool34(hx3) + + #stage 4 + hx4 = self.stage4(hx) + hx = self.pool45(hx4) + + #stage 5 + hx5 = self.stage5(hx) + hx = self.pool56(hx5) + + #stage 6 + hx6 = self.stage6(hx) + hx6up = _upsample_like(hx6, hx5) + + #-------------------- decoder -------------------- + hx5d = self.stage5d(paddle.concat((hx6up, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.stage4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.stage3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.stage2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.stage1d(paddle.concat((hx2dup, hx1), 1)) + + #side output + d1 = self.side1(hx1d) + + d2 = self.side2(hx2d) + d2 = _upsample_like(d2, d1) + + d3 = self.side3(hx3d) + d3 = _upsample_like(d3, d1) + + d4 = self.side4(hx4d) + d4 = _upsample_like(d4, d1) + + d5 = self.side5(hx5d) + d5 = _upsample_like(d5, d1) + + d6 = self.side6(hx6) + d6 = _upsample_like(d6, d1) + + d0 = self.outconv(paddle.concat((d1, d2, d3, d4, d5, d6), 1)) + + return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) + + +### U^2-Net small ### +class U2NETP(nn.Layer): + def __init__(self, in_ch=3, out_ch=1): + super(U2NETP, self).__init__() + + self.stage1 = RSU7(in_ch, 16, 64) + self.pool12 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage2 = RSU6(64, 16, 64) + self.pool23 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage3 = RSU5(64, 16, 64) + self.pool34 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage4 = RSU4(64, 16, 64) + self.pool45 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage5 = RSU4F(64, 16, 64) + self.pool56 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage6 = RSU4F(64, 16, 64) + + # decoder + self.stage5d = RSU4F(128, 16, 64) + self.stage4d = RSU4(128, 16, 64) + self.stage3d = RSU5(128, 16, 64) + self.stage2d = RSU6(128, 16, 64) + self.stage1d = RSU7(128, 16, 64) + + self.side1 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side2 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side3 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side4 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side5 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side6 = nn.Conv2D(64, out_ch, 3, padding=1) + + self.outconv = nn.Conv2D(6, out_ch, 1) + + def forward(self, x): + + hx = x + + #stage 1 + hx1 = self.stage1(hx) + hx = self.pool12(hx1) + + #stage 2 + hx2 = self.stage2(hx) + hx = self.pool23(hx2) + + #stage 3 + hx3 = self.stage3(hx) + hx = self.pool34(hx3) + + #stage 4 + hx4 = self.stage4(hx) + hx = self.pool45(hx4) + + #stage 5 + hx5 = self.stage5(hx) + hx = self.pool56(hx5) + + #stage 6 + hx6 = self.stage6(hx) + hx6up = _upsample_like(hx6, hx5) + + #decoder + hx5d = self.stage5d(paddle.concat((hx6up, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.stage4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.stage3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.stage2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.stage1d(paddle.concat((hx2dup, hx1), 1)) + + #side output + d1 = self.side1(hx1d) + + d2 = self.side2(hx2d) + d2 = _upsample_like(d2, d1) + + d3 = self.side3(hx3d) + d3 = _upsample_like(d3, d1) + + d4 = self.side4(hx4d) + d4 = _upsample_like(d4, d1) + + d5 = self.side5(hx5d) + d5 = _upsample_like(d5, d1) + + d6 = self.side6(hx6) + d6 = _upsample_like(d6, d1) + + d0 = self.outconv(paddle.concat((d1, d2, d3, d4, d5, d6), 1)) + + return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) diff --git a/modules/image/semantic_segmentation/U2Netp/README.md b/modules/thirdparty/image/semantic_segmentation/U2Netp/README.md similarity index 100% rename from modules/image/semantic_segmentation/U2Netp/README.md rename to modules/thirdparty/image/semantic_segmentation/U2Netp/README.md diff --git a/modules/image/semantic_segmentation/U2Netp/module.py b/modules/thirdparty/image/semantic_segmentation/U2Netp/module.py similarity index 62% rename from modules/image/semantic_segmentation/U2Netp/module.py rename to modules/thirdparty/image/semantic_segmentation/U2Netp/module.py index 49abc5f5f2a922b5318c3ec3b62f6d6ccc2b9c72..ae8939c34cf6deac628ac129ed8120220a47e8c6 100644 --- a/modules/image/semantic_segmentation/U2Netp/module.py +++ b/modules/thirdparty/image/semantic_segmentation/U2Netp/module.py @@ -6,18 +6,19 @@ from U2Netp.u2net import U2NETP from U2Netp.processor import Processor from paddlehub.module.module import moduleinfo + @moduleinfo( - name="U2Netp", # 模型名称 - type="CV", # 模型类型 - author="jm12138", # 作者名称 - author_email="jm12138@qq.com", # 作者邮箱 - summary="U2Netp", # 模型介绍 - version="1.0.0" # 版本号 + name="U2Netp", # 模型名称 + type="CV", # 模型类型 + author="jm12138", # 作者名称 + author_email="jm12138@qq.com", # 作者邮箱 + summary="U2Netp", # 模型介绍 + version="1.0.0" # 版本号 ) class U2Netp(nn.Layer): def __init__(self): super(U2Netp, self).__init__() - self.model = U2NETP(3,1) + self.model = U2NETP(3, 1) state_dict = paddle.load(os.path.join(self.directory, 'u2netp.pdparams')) self.model.set_dict(state_dict) self.model.eval() @@ -26,21 +27,20 @@ class U2Netp(nn.Layer): outputs = [] for data in input_datas: data = paddle.to_tensor(data, 'float32') - d1,d2,d3,d4,d5,d6,d7= self.model(data) + d1, d2, d3, d4, d5, d6, d7 = self.model(data) outputs.append(d1.numpy()) outputs = np.concatenate(outputs, 0) - + return outputs - def Segmentation( - self, - images=None, - paths=None, - batch_size=1, - input_size=320, - output_dir='output', - visualization=False): + def Segmentation(self, + images=None, + paths=None, + batch_size=1, + input_size=320, + output_dir='output', + visualization=False): # 初始化数据处理器 processor = Processor(paths, images, batch_size, input_size) diff --git a/modules/image/semantic_segmentation/U2Netp/processor.py b/modules/thirdparty/image/semantic_segmentation/U2Netp/processor.py similarity index 69% rename from modules/image/semantic_segmentation/U2Netp/processor.py rename to modules/thirdparty/image/semantic_segmentation/U2Netp/processor.py index a6cef1ae1a98c95e2170e2b6842d76c481e5cb0c..949f119e7990c9453d84587c0109e27a61271744 100644 --- a/modules/image/semantic_segmentation/U2Netp/processor.py +++ b/modules/thirdparty/image/semantic_segmentation/U2Netp/processor.py @@ -4,6 +4,7 @@ import numpy as np __all__ = ['Processor'] + class Processor(): def __init__(self, paths, images, batch_size, input_size): # 图像列表 @@ -25,7 +26,7 @@ class Processor(): if images is not None: datas = images - + # 返回数据列表 return datas @@ -34,22 +35,22 @@ class Processor(): input_datas = [] for image in imgs: image = cv2.resize(image, (input_size, input_size)) - tmpImg = np.zeros((image.shape[0],image.shape[1],3)) - image = image/np.max(image) + tmpImg = np.zeros((image.shape[0], image.shape[1], 3)) + image = image / np.max(image) - tmpImg[:,:,0] = (image[:,:,0]-0.485)/0.229 - tmpImg[:,:,1] = (image[:,:,1]-0.456)/0.224 - tmpImg[:,:,2] = (image[:,:,2]-0.406)/0.225 + tmpImg[:, :, 0] = (image[:, :, 0] - 0.485) / 0.229 + tmpImg[:, :, 1] = (image[:, :, 1] - 0.456) / 0.224 + tmpImg[:, :, 2] = (image[:, :, 2] - 0.406) / 0.225 # convert BGR to RGB tmpImg = tmpImg.transpose((2, 0, 1)) - tmpImg = tmpImg[np.newaxis,:,:,:] + tmpImg = tmpImg[np.newaxis, :, :, :] input_datas.append(tmpImg) - + input_datas = np.concatenate(input_datas, 0) datas_num = input_datas.shape[0] - split_num = datas_num//batch_size+1 if datas_num%batch_size!=0 else datas_num//batch_size + split_num = datas_num // batch_size + 1 if datas_num % batch_size != 0 else datas_num // batch_size input_datas = np.array_split(input_datas, split_num) @@ -59,7 +60,7 @@ class Processor(): ma = np.max(d) mi = np.min(d) - dn = (d-mi)/(ma-mi) + dn = (d - mi) / (ma - mi) return dn @@ -68,10 +69,10 @@ class Processor(): results = [] if visualization and not os.path.exists(output_dir): os.mkdir(output_dir) - + for i, image in enumerate(self.imgs): # normalization - pred = outputs[i,0,:,:] + pred = outputs[i, 0, :, :] pred = self.normPRED(pred) @@ -79,17 +80,14 @@ class Processor(): h, w = image.shape[:2] mask = cv2.resize(pred, (w, h)) - output_img = (image*mask[..., np.newaxis] + (1-mask[..., np.newaxis])*255).astype(np.uint8) + output_img = (image * mask[..., np.newaxis] + (1 - mask[..., np.newaxis]) * 255).astype(np.uint8) + + mask = (mask * 255).astype(np.uint8) - mask = (mask*255).astype(np.uint8) - if visualization: cv2.imwrite(os.path.join(output_dir, 'result_mask_%d.png' % i), mask) cv2.imwrite(os.path.join(output_dir, 'result_%d.png' % i), output_img) - results.append({ - 'mask': mask, - 'front': output_img - }) - - return results \ No newline at end of file + results.append({'mask': mask, 'front': output_img}) + + return results diff --git a/modules/thirdparty/image/semantic_segmentation/U2Netp/u2net.py b/modules/thirdparty/image/semantic_segmentation/U2Netp/u2net.py new file mode 100644 index 0000000000000000000000000000000000000000..3a7ecd0e90d4386df33f532833ceca48fc0d62a0 --- /dev/null +++ b/modules/thirdparty/image/semantic_segmentation/U2Netp/u2net.py @@ -0,0 +1,524 @@ +import paddle +import paddle.nn as nn +import paddle.nn.functional as F + +__all__ = ['U2NETP', 'U2NET'] + + +class REBNCONV(nn.Layer): + def __init__(self, in_ch=3, out_ch=3, dirate=1): + super(REBNCONV, self).__init__() + + self.conv_s1 = nn.Conv2D(in_ch, out_ch, 3, padding=1 * dirate, dilation=1 * dirate) + self.bn_s1 = nn.BatchNorm2D(out_ch) + self.relu_s1 = nn.ReLU() + + def forward(self, x): + + hx = x + xout = self.relu_s1(self.bn_s1(self.conv_s1(hx))) + + return xout + + +## upsample tensor 'src' to have the same spatial size with tensor 'tar' +def _upsample_like(src, tar): + + src = F.upsample(src, size=tar.shape[2:], mode='bilinear') + + return src + + +### RSU-7 ### +class RSU7(nn.Layer): #UNet07DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU7, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool4 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool5 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv7 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv6d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + hx = self.pool4(hx4) + + hx5 = self.rebnconv5(hx) + hx = self.pool5(hx5) + + hx6 = self.rebnconv6(hx) + + hx7 = self.rebnconv7(hx6) + + hx6d = self.rebnconv6d(paddle.concat((hx7, hx6), 1)) + hx6dup = _upsample_like(hx6d, hx5) + + hx5d = self.rebnconv5d(paddle.concat((hx6dup, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-6 ### +class RSU6(nn.Layer): #UNet06DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU6, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool4 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv5d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + hx = self.pool4(hx4) + + hx5 = self.rebnconv5(hx) + + hx6 = self.rebnconv6(hx5) + + hx5d = self.rebnconv5d(paddle.concat((hx6, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-5 ### +class RSU5(nn.Layer): #UNet05DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU5, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool3 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv4d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + hx = self.pool3(hx3) + + hx4 = self.rebnconv4(hx) + + hx5 = self.rebnconv5(hx4) + + hx4d = self.rebnconv4d(paddle.concat((hx5, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-4 ### +class RSU4(nn.Layer): #UNet04DRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU4, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.pool1 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1) + self.pool2 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=2) + + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=1) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx = self.pool1(hx1) + + hx2 = self.rebnconv2(hx) + hx = self.pool2(hx2) + + hx3 = self.rebnconv3(hx) + + hx4 = self.rebnconv4(hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.rebnconv2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.rebnconv1d(paddle.concat((hx2dup, hx1), 1)) + + return hx1d + hxin + + +### RSU-4F ### +class RSU4F(nn.Layer): #UNet04FRES(nn.Layer): + def __init__(self, in_ch=3, mid_ch=12, out_ch=3): + super(RSU4F, self).__init__() + + self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1) + + self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1) + self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=2) + self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=4) + + self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=8) + + self.rebnconv3d = REBNCONV(mid_ch * 2, mid_ch, dirate=4) + self.rebnconv2d = REBNCONV(mid_ch * 2, mid_ch, dirate=2) + self.rebnconv1d = REBNCONV(mid_ch * 2, out_ch, dirate=1) + + def forward(self, x): + + hx = x + + hxin = self.rebnconvin(hx) + + hx1 = self.rebnconv1(hxin) + hx2 = self.rebnconv2(hx1) + hx3 = self.rebnconv3(hx2) + + hx4 = self.rebnconv4(hx3) + + hx3d = self.rebnconv3d(paddle.concat((hx4, hx3), 1)) + hx2d = self.rebnconv2d(paddle.concat((hx3d, hx2), 1)) + hx1d = self.rebnconv1d(paddle.concat((hx2d, hx1), 1)) + + return hx1d + hxin + + +##### U^2-Net #### +class U2NET(nn.Layer): + def __init__(self, in_ch=3, out_ch=1): + super(U2NET, self).__init__() + + self.stage1 = RSU7(in_ch, 32, 64) + self.pool12 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage2 = RSU6(64, 32, 128) + self.pool23 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage3 = RSU5(128, 64, 256) + self.pool34 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage4 = RSU4(256, 128, 512) + self.pool45 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage5 = RSU4F(512, 256, 512) + self.pool56 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage6 = RSU4F(512, 256, 512) + + # decoder + self.stage5d = RSU4F(1024, 256, 512) + self.stage4d = RSU4(1024, 128, 256) + self.stage3d = RSU5(512, 64, 128) + self.stage2d = RSU6(256, 32, 64) + self.stage1d = RSU7(128, 16, 64) + + self.side1 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side2 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side3 = nn.Conv2D(128, out_ch, 3, padding=1) + self.side4 = nn.Conv2D(256, out_ch, 3, padding=1) + self.side5 = nn.Conv2D(512, out_ch, 3, padding=1) + self.side6 = nn.Conv2D(512, out_ch, 3, padding=1) + + self.outconv = nn.Conv2D(6, out_ch, 1) + + def forward(self, x): + + hx = x + + #stage 1 + hx1 = self.stage1(hx) + hx = self.pool12(hx1) + + #stage 2 + hx2 = self.stage2(hx) + hx = self.pool23(hx2) + + #stage 3 + hx3 = self.stage3(hx) + hx = self.pool34(hx3) + + #stage 4 + hx4 = self.stage4(hx) + hx = self.pool45(hx4) + + #stage 5 + hx5 = self.stage5(hx) + hx = self.pool56(hx5) + + #stage 6 + hx6 = self.stage6(hx) + hx6up = _upsample_like(hx6, hx5) + + #-------------------- decoder -------------------- + hx5d = self.stage5d(paddle.concat((hx6up, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.stage4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.stage3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.stage2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.stage1d(paddle.concat((hx2dup, hx1), 1)) + + #side output + d1 = self.side1(hx1d) + + d2 = self.side2(hx2d) + d2 = _upsample_like(d2, d1) + + d3 = self.side3(hx3d) + d3 = _upsample_like(d3, d1) + + d4 = self.side4(hx4d) + d4 = _upsample_like(d4, d1) + + d5 = self.side5(hx5d) + d5 = _upsample_like(d5, d1) + + d6 = self.side6(hx6) + d6 = _upsample_like(d6, d1) + + d0 = self.outconv(paddle.concat((d1, d2, d3, d4, d5, d6), 1)) + + return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) + + +### U^2-Net small ### +class U2NETP(nn.Layer): + def __init__(self, in_ch=3, out_ch=1): + super(U2NETP, self).__init__() + + self.stage1 = RSU7(in_ch, 16, 64) + self.pool12 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage2 = RSU6(64, 16, 64) + self.pool23 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage3 = RSU5(64, 16, 64) + self.pool34 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage4 = RSU4(64, 16, 64) + self.pool45 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage5 = RSU4F(64, 16, 64) + self.pool56 = nn.MaxPool2D(2, stride=2, ceil_mode=True) + + self.stage6 = RSU4F(64, 16, 64) + + # decoder + self.stage5d = RSU4F(128, 16, 64) + self.stage4d = RSU4(128, 16, 64) + self.stage3d = RSU5(128, 16, 64) + self.stage2d = RSU6(128, 16, 64) + self.stage1d = RSU7(128, 16, 64) + + self.side1 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side2 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side3 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side4 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side5 = nn.Conv2D(64, out_ch, 3, padding=1) + self.side6 = nn.Conv2D(64, out_ch, 3, padding=1) + + self.outconv = nn.Conv2D(6, out_ch, 1) + + def forward(self, x): + + hx = x + + #stage 1 + hx1 = self.stage1(hx) + hx = self.pool12(hx1) + + #stage 2 + hx2 = self.stage2(hx) + hx = self.pool23(hx2) + + #stage 3 + hx3 = self.stage3(hx) + hx = self.pool34(hx3) + + #stage 4 + hx4 = self.stage4(hx) + hx = self.pool45(hx4) + + #stage 5 + hx5 = self.stage5(hx) + hx = self.pool56(hx5) + + #stage 6 + hx6 = self.stage6(hx) + hx6up = _upsample_like(hx6, hx5) + + #decoder + hx5d = self.stage5d(paddle.concat((hx6up, hx5), 1)) + hx5dup = _upsample_like(hx5d, hx4) + + hx4d = self.stage4d(paddle.concat((hx5dup, hx4), 1)) + hx4dup = _upsample_like(hx4d, hx3) + + hx3d = self.stage3d(paddle.concat((hx4dup, hx3), 1)) + hx3dup = _upsample_like(hx3d, hx2) + + hx2d = self.stage2d(paddle.concat((hx3dup, hx2), 1)) + hx2dup = _upsample_like(hx2d, hx1) + + hx1d = self.stage1d(paddle.concat((hx2dup, hx1), 1)) + + #side output + d1 = self.side1(hx1d) + + d2 = self.side2(hx2d) + d2 = _upsample_like(d2, d1) + + d3 = self.side3(hx3d) + d3 = _upsample_like(d3, d1) + + d4 = self.side4(hx4d) + d4 = _upsample_like(d4, d1) + + d5 = self.side5(hx5d) + d5 = _upsample_like(d5, d1) + + d6 = self.side6(hx6) + d6 = _upsample_like(d6, d1) + + d0 = self.outconv(paddle.concat((d1, d2, d3, d4, d5, d6), 1)) + + return F.sigmoid(d0), F.sigmoid(d1), F.sigmoid(d2), F.sigmoid(d3), F.sigmoid(d4), F.sigmoid(d5), F.sigmoid(d6) diff --git a/modules/text/text_generation/CPM_LM/GPT2/__init__.py b/modules/thirdparty/text/text_generation/CPM_LM/GPT2/__init__.py similarity index 100% rename from modules/text/text_generation/CPM_LM/GPT2/__init__.py rename to modules/thirdparty/text/text_generation/CPM_LM/GPT2/__init__.py diff --git a/modules/text/text_generation/CPM_LM/GPT2/bpe/chinese_vocab.model b/modules/thirdparty/text/text_generation/CPM_LM/GPT2/bpe/chinese_vocab.model similarity index 100% rename from modules/text/text_generation/CPM_LM/GPT2/bpe/chinese_vocab.model rename to modules/thirdparty/text/text_generation/CPM_LM/GPT2/bpe/chinese_vocab.model diff --git a/modules/text/text_generation/CPM_LM/GPT2/bpe/vocab.json b/modules/thirdparty/text/text_generation/CPM_LM/GPT2/bpe/vocab.json similarity index 100% rename from modules/text/text_generation/CPM_LM/GPT2/bpe/vocab.json rename to modules/thirdparty/text/text_generation/CPM_LM/GPT2/bpe/vocab.json diff --git a/modules/text/text_generation/CPM_LM/GPT2/model.py b/modules/thirdparty/text/text_generation/CPM_LM/GPT2/model.py similarity index 71% rename from modules/text/text_generation/CPM_LM/GPT2/model.py rename to modules/thirdparty/text/text_generation/CPM_LM/GPT2/model.py index 02e88cb991bd0de516b8abab48a4bd0771a5a292..136c21d7292551b9602579db183efb13f21d9d98 100644 --- a/modules/text/text_generation/CPM_LM/GPT2/model.py +++ b/modules/thirdparty/text/text_generation/CPM_LM/GPT2/model.py @@ -2,11 +2,12 @@ import math import paddle import paddle.nn as nn + class MLP(nn.Layer): def __init__(self, embedding_size): super(MLP, self).__init__() - self.dense_h_to_4h = nn.Linear(embedding_size, embedding_size*4) - self.dense_4h_to_h = nn.Linear(embedding_size*4, embedding_size) + self.dense_h_to_4h = nn.Linear(embedding_size, embedding_size * 4) + self.dense_4h_to_h = nn.Linear(embedding_size * 4, embedding_size) self.act = nn.functional.gelu def forward(self, x): @@ -14,12 +15,9 @@ class MLP(nn.Layer): h2 = self.dense_4h_to_h(h) return h2 + class Attention(nn.Layer): - def __init__(self, - embedding_size, - num_attention_heads, - attention_dropout, - residual_dropout): + def __init__(self, embedding_size, num_attention_heads, attention_dropout, residual_dropout): super(Attention, self).__init__() self.num_attention_heads = num_attention_heads self.size_per_head = embedding_size // num_attention_heads @@ -38,11 +36,11 @@ class Attention(nn.Layer): self.seq_len = x.shape[1] x = self.query_key_value(x) q, k, v = x.split(num_or_sections=3, axis=2) - + q = self.split_heads(q) k = self.split_heads(k) v = self.split_heads(v) - + if kv_cache is not None: pk, pv = paddle.unstack(kv_cache, axis=1) k = paddle.concat([pk, k], axis=-2) @@ -69,12 +67,9 @@ class Attention(nn.Layer): return y, cached_kv + class Block(nn.Layer): - def __init__(self, - embedding_size, - num_attention_heads, - attention_dropout, - residual_dropout): + def __init__(self, embedding_size, num_attention_heads, attention_dropout, residual_dropout): super(Block, self).__init__() self.input_layernorm = nn.LayerNorm(embedding_size, epsilon=1e-5) self.attention = Attention(embedding_size, num_attention_heads, attention_dropout, residual_dropout) @@ -89,24 +84,17 @@ class Block(nn.Layer): x = x + z return x, cached_kv + class Transformer(nn.Layer): - def __init__(self, - layer_size, - embedding_size, - num_attention_heads, - attention_dropout, - residual_dropout): + def __init__(self, layer_size, embedding_size, num_attention_heads, attention_dropout, residual_dropout): super(Transformer, self).__init__() - self.layers = nn.LayerList([Block( - embedding_size, - num_attention_heads, - attention_dropout, - residual_dropout) - for _ in range(layer_size)]) + self.layers = nn.LayerList([ + Block(embedding_size, num_attention_heads, attention_dropout, residual_dropout) for _ in range(layer_size) + ]) self.final_layernorm = nn.LayerNorm(embedding_size, epsilon=1e-5) - + def forward(self, x, kv_cache=None): cached_kvs = [] for i, layer in enumerate(self.layers): @@ -115,26 +103,16 @@ class Transformer(nn.Layer): x = self.final_layernorm(x) return x, paddle.stack(cached_kvs) + class GPT2Model(nn.Layer): - def __init__(self, - vocab_size, - layer_size, - block_size, - embedding_dropout, - embedding_size, - num_attention_heads, - attention_dropout, - residual_dropout): + def __init__(self, vocab_size, layer_size, block_size, embedding_dropout, embedding_size, num_attention_heads, + attention_dropout, residual_dropout): super(GPT2Model, self).__init__() self.word_embeddings = nn.Embedding(vocab_size, embedding_size) self.position_embeddings = nn.Embedding(block_size, embedding_size) self.emb_drop = nn.Dropout(embedding_dropout) - self.transformer = Transformer( - layer_size, - embedding_size, - num_attention_heads, - attention_dropout, - residual_dropout) + self.transformer = Transformer(layer_size, embedding_size, num_attention_heads, attention_dropout, + residual_dropout) def forward(self, x, kv_cache=None, use_cache=False): if kv_cache is None: @@ -155,16 +133,17 @@ class GPT2Model(nn.Layer): else: return x + if __name__ == '__main__': gpt = GPT2Model( - vocab_size=30000, - layer_size=2, - block_size=1024, - embedding_dropout=0.0, - embedding_size=2560, - num_attention_heads=32, - attention_dropout=0.0, - residual_dropout=0.0) + vocab_size=30000, + layer_size=2, + block_size=1024, + embedding_dropout=0.0, + embedding_size=2560, + num_attention_heads=32, + attention_dropout=0.0, + residual_dropout=0.0) gpt.eval() - out, cached_kvs = gpt(paddle.ones([1,1], 'int64'), paddle.randn([32, 1, 2, 32, 9, 80], 'float32'), use_cache=True) + out, cached_kvs = gpt(paddle.ones([1, 1], 'int64'), paddle.randn([32, 1, 2, 32, 9, 80], 'float32'), use_cache=True) print(out.shape, cached_kvs.shape) diff --git a/modules/text/text_generation/CPM_LM/GPT2/tokenization.py b/modules/thirdparty/text/text_generation/CPM_LM/GPT2/tokenization.py similarity index 95% rename from modules/text/text_generation/CPM_LM/GPT2/tokenization.py rename to modules/thirdparty/text/text_generation/CPM_LM/GPT2/tokenization.py index 681fc7a786d793a96b882aab1022fb0888a5ce9e..e979e6c340630f0ec0cf5159a3d9061b823021a8 100644 --- a/modules/text/text_generation/CPM_LM/GPT2/tokenization.py +++ b/modules/thirdparty/text/text_generation/CPM_LM/GPT2/tokenization.py @@ -13,8 +13,7 @@ # See the License for the specific language governing permissions and # limitations under the License. """Tokenization classes for OpenAI GPT.""" -from __future__ import (absolute_import, division, print_function, - unicode_literals) +from __future__ import (absolute_import, division, print_function, unicode_literals) import json from io import open @@ -29,11 +28,12 @@ except ImportError: def lru_cache(): return lambda func: func + class GPT2Tokenizer(object): def __init__(self, vocab_file, model_file, max_len=None): self.max_len = max_len if max_len is not None else int(1e12) self.encoder = json.load(open(vocab_file)) - self.decoder = {v:k for k,v in self.encoder.items()} + self.decoder = {v: k for k, v in self.encoder.items()} self.sp = spm.SentencePieceProcessor(model_file=model_file) self.translator = str.maketrans(" \n", "\u2582\u2583") diff --git a/modules/text/text_generation/CPM_LM/README.md b/modules/thirdparty/text/text_generation/CPM_LM/README.md similarity index 93% rename from modules/text/text_generation/CPM_LM/README.md rename to modules/thirdparty/text/text_generation/CPM_LM/README.md index 4443a2c7361a4c5600921518df2c8251d0ac8dbd..f9f88742a3b523d3ff4e7b44abda7c778fb8cbaa 100644 --- a/modules/text/text_generation/CPM_LM/README.md +++ b/modules/thirdparty/text/text_generation/CPM_LM/README.md @@ -8,8 +8,8 @@ CPM-LM 是一个基于 GPT-2 的预训练生成模型，参数规模达 26 亿 ## API ```python def greedy_search( - text, - max_len=32, + text, + max_len=32, end_word=None): ``` 文本生成 API ，根据输入的文字进行文本生成，使用 Greedy Search 进行解码，生成的文本单一且确定，适合于问答类的文本生成。 @@ -24,12 +24,12 @@ def greedy_search( ```python def sample( - text, - max_len=32, - end_word=None, - repitition_penalty=1.0, - temperature=1.0, - top_k=0, + text, + max_len=32, + end_word=None, + repitition_penalty=1.0, + temperature=1.0, + top_k=0, top_p=1.0): ``` 文本生成 API ，根据输入的文字进行文本生成，使用采样的方式进行解码，生成的文本比较多样，适合于文章类的文本生成。 @@ -137,4 +137,4 @@ https://github.com/jm12138/CPM-Generate-Paddle ## 依赖 paddlepaddle >= 2.0.0rc0 -paddlehub >= 2.0.0b1 \ No newline at end of file +paddlehub >= 2.0.0b1 diff --git a/modules/text/text_generation/CPM_LM/module.py b/modules/thirdparty/text/text_generation/CPM_LM/module.py similarity index 87% rename from modules/text/text_generation/CPM_LM/module.py rename to modules/thirdparty/text/text_generation/CPM_LM/module.py index 00a3098be721d0148c56ee9f02a5c42d43b07d25..1351e6616aaff4f19883564c005f3129d01a51be 100644 --- a/modules/text/text_generation/CPM_LM/module.py +++ b/modules/thirdparty/text/text_generation/CPM_LM/module.py @@ -5,13 +5,14 @@ from paddle.nn import Layer from paddlehub.module.module import moduleinfo from CPM_LM.GPT2 import GPT2Model, GPT2Tokenizer + @moduleinfo( - name="CPM_LM", # 模型名称 - type="NLP/NLG", # 模型类型 - author="jm12138", # 作者名称 - author_email="jm12138@qq.com", # 作者邮箱 - summary="CPM_LM", # 模型介绍 - version="1.0.1" # 版本号 + name="CPM_LM", # 模型名称 + type="NLP/NLG", # 模型类型 + author="jm12138", # 作者名称 + author_email="jm12138@qq.com", # 作者邮箱 + summary="CPM_LM", # 模型介绍 + version="1.0.1" # 版本号 ) class CPM_LM(Layer): def __init__(self, max_len=512): @@ -56,7 +57,7 @@ class CPM_LM(Layer): if end_word is not None: stop_id = self.tokenizer.encode(end_word) length = len(stop_id) - + # 初始预测 ids = self.tokenizer.encode(text) input_id = paddle.to_tensor(np.array(ids).reshape(1, -1).astype('int64')) @@ -65,17 +66,17 @@ class CPM_LM(Layer): ids.append(next_token) # 使用缓存进行继续预测 - for i in range(max_len-1): + for i in range(max_len - 1): input_id = paddle.to_tensor(np.array([next_token]).reshape(1, -1).astype('int64')) output, cached_kvs = self.model(input_id, cached_kvs, use_cache=True) next_token = int(np.argmax(output[0, -1].numpy())) ids.append(next_token) - if next_token==end_id: + if next_token == end_id: break # 根据终止标志停止预测 - if (end_word is not None) and (ids[-length:]==stop_id): + if (end_word is not None) and (ids[-length:] == stop_id): break return self.tokenizer.decode(ids) @@ -135,7 +136,7 @@ class CPM_LM(Layer): ids += [int(next_token)] # 使用缓存进行继续预测 - for i in range(max_len-1): + for i in range(max_len - 1): input_id = paddle.to_tensor(np.array([next_token]).reshape(1, -1).astype('int64')) output, cached_kvs = self.model(input_id, cached_kvs, use_cache=True) next_token_logits = output[0, -1, :] @@ -144,14 +145,15 @@ class CPM_LM(Layer): next_token_logits = next_token_logits / temperature next_token_logits[self.tokenizer.encoder['']] = -float('Inf') filtered_logits = self.top_k_top_p_filtering(next_token_logits, top_k=top_k, top_p=top_p) - next_token = paddle.multinomial(paddle.nn.functional.softmax(filtered_logits, axis=-1), num_samples=1).numpy() + next_token = paddle.multinomial( + paddle.nn.functional.softmax(filtered_logits, axis=-1), num_samples=1).numpy() ids += [int(next_token)] - - if next_token==end_id: + + if next_token == end_id: break # 根据终止标志停止预测 - if (end_word is not None) and (ids[-length:]==stop_id): + if (end_word is not None) and (ids[-length:] == stop_id): break - return self.tokenizer.decode(ids) \ No newline at end of file + return self.tokenizer.decode(ids) diff --git a/modules/text/text_generation/reading_pictures_writing_poems/README.md b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems/README.md similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems/README.md rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems/README.md diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnDetection/__init__.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems/__init__.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnDetection/__init__.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems/__init__.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems/module.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems/module.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems/module.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems/module.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/__init__.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnDetection/__init__.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/__init__.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnDetection/__init__.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnDetection/module.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnDetection/module.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnDetection/module.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnDetection/module.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/__init__.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/__init__.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/__init__.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/__init__.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/decode.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/decode.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/decode.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/decode.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/file_utils.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/file_utils.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/file_utils.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/file_utils.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/modeling_ernie.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/modeling_ernie.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/modeling_ernie.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/modeling_ernie.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/modeling_ernie_gen.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/modeling_ernie_gen.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/modeling_ernie_gen.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/modeling_ernie_gen.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/tokenizing_ernie.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/tokenizing_ernie.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/tokenizing_ernie.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/model/tokenizing_ernie.py diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/module.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/module.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/module.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/MidAutumnPoetry/module.py diff --git a/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/__init__.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/module.py b/modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/module.py similarity index 100% rename from modules/text/text_generation/reading_pictures_writing_poems_for_midautumn/module.py rename to modules/thirdparty/text/text_generation/reading_pictures_writing_poems_for_midautumn/module.py diff --git a/paddlehub/__init__.py b/paddlehub/__init__.py index c447588375cf179375e228648e08f561fac39d41..2b7ea4207a2202fcd1aaf4114035fa0219b919cb 100644 --- a/paddlehub/__init__.py +++ b/paddlehub/__init__.py @@ -17,7 +17,7 @@ import sys from easydict import EasyDict -__version__ = '2.0.0-beta0' +__version__ = '2.0.0-beta2' from paddlehub import env from paddlehub.config import config