From a689b8dd0e82c548efdebbec928a6f15717cc450 Mon Sep 17 00:00:00 2001 From: chenguowei01 Date: Thu, 18 Jun 2020 14:47:39 +0800 Subject: [PATCH] add mult grid and rgb change --- pdseg/models/backbone/resnet_vd.py | 253 ++++++++++++++--------------- pdseg/reader.py | 2 + pdseg/utils/config.py | 2 + 3 files changed, 130 insertions(+), 127 deletions(-) diff --git a/pdseg/models/backbone/resnet_vd.py b/pdseg/models/backbone/resnet_vd.py index 8d684656..827dad5b 100644 --- a/pdseg/models/backbone/resnet_vd.py +++ b/pdseg/models/backbone/resnet_vd.py @@ -65,6 +65,7 @@ class ResNet(): dilation_dict=None): layers = self.layers supported_layers = [18, 34, 50, 101, 152] + mult_grid = [1, 2, 4] assert layers in supported_layers, \ "supported layers are {} but input layer is {}".format(supported_layers, layers) @@ -96,37 +97,42 @@ class ResNet(): num_filters = [64, 128, 256, 512] if self.stem == 'icnet' or self.stem == 'pspnet' or self.stem == 'deeplab': - conv = self.conv_bn_layer(input=input, - num_filters=int(32 * self.scale), - filter_size=3, - stride=2, - act='relu', - name="conv1_1") - conv = self.conv_bn_layer(input=conv, - num_filters=int(32 * self.scale), - filter_size=3, - stride=1, - act='relu', - name="conv1_2") - conv = self.conv_bn_layer(input=conv, - num_filters=int(64 * self.scale), - filter_size=3, - stride=1, - act='relu', - name="conv1_3") + conv = self.conv_bn_layer( + input=input, + num_filters=int(32 * self.scale), + filter_size=3, + stride=2, + act='relu', + name="conv1_1") + conv = self.conv_bn_layer( + input=conv, + num_filters=int(32 * self.scale), + filter_size=3, + stride=1, + act='relu', + name="conv1_2") + conv = self.conv_bn_layer( + input=conv, + num_filters=int(64 * self.scale), + filter_size=3, + stride=1, + act='relu', + name="conv1_3") else: - conv = self.conv_bn_layer(input=input, - num_filters=int(64 * self.scale), - filter_size=7, - stride=2, - act='relu', - name="conv1") - - conv = fluid.layers.pool2d(input=conv, - pool_size=3, - pool_stride=2, - pool_padding=1, - pool_type='max') + conv = self.conv_bn_layer( + input=input, + num_filters=int(64 * self.scale), + filter_size=7, + stride=2, + act='relu', + name="conv1") + + conv = fluid.layers.pool2d( + input=conv, + pool_size=3, + pool_stride=2, + pool_padding=1, + pool_type='max') layer_count = 1 if check_points(layer_count, decode_points): @@ -147,6 +153,8 @@ class ResNet(): else: conv_name = "res" + str(block + 2) + chr(97 + i) dilation_rate = get_dilated_rate(dilation_dict, block) + if block == 3: + dilation_rate = dilation_rate * mult_grid[i] conv = self.bottleneck_block( input=conv, @@ -170,10 +178,8 @@ class ResNet(): np.ceil( np.array(conv.shape[2:]).astype('int32') / 2)) - pool = fluid.layers.pool2d(input=conv, - pool_size=7, - pool_type='avg', - global_pooling=True) + pool = fluid.layers.pool2d( + input=conv, pool_size=7, pool_type='avg', global_pooling=True) stdv = 1.0 / math.sqrt(pool.shape[1] * 1.0) out = fluid.layers.fc( input=pool, @@ -198,10 +204,8 @@ class ResNet(): if check_points(layer_count, end_points): return conv, decode_ends - pool = fluid.layers.pool2d(input=conv, - pool_size=7, - pool_type='avg', - global_pooling=True) + pool = fluid.layers.pool2d( + input=conv, pool_size=7, pool_type='avg', global_pooling=True) stdv = 1.0 / math.sqrt(pool.shape[1] * 1.0) out = fluid.layers.fc( input=pool, @@ -234,19 +238,18 @@ class ResNet(): else: bias_attr = False - conv = fluid.layers.conv2d(input=input, - num_filters=num_filters, - filter_size=filter_size, - stride=stride, - padding=(filter_size - 1) // - 2 if dilation == 1 else 0, - dilation=dilation, - groups=groups, - act=None, - param_attr=ParamAttr(name=name + "_weights", - learning_rate=lr_mult), - bias_attr=bias_attr, - name=name + '.conv2d.output.1') + conv = fluid.layers.conv2d( + input=input, + num_filters=num_filters, + filter_size=filter_size, + stride=stride, + padding=(filter_size - 1) // 2 if dilation == 1 else 0, + dilation=dilation, + groups=groups, + act=None, + param_attr=ParamAttr(name=name + "_weights", learning_rate=lr_mult), + bias_attr=bias_attr, + name=name + '.conv2d.output.1') if name == "conv1": bn_name = "bn_" + name @@ -256,8 +259,8 @@ class ResNet(): input=conv, act=act, name=bn_name + '.output.1', - param_attr=ParamAttr(name=bn_name + '_scale', - learning_rate=lr_mult), + param_attr=ParamAttr( + name=bn_name + '_scale', learning_rate=lr_mult), bias_attr=ParamAttr(bn_name + '_offset', learning_rate=lr_mult), moving_mean_name=bn_name + '_mean', moving_variance_name=bn_name + '_variance', @@ -272,23 +275,24 @@ class ResNet(): act=None, name=None): lr_mult = self.lr_mult_list[self.curr_stage] - pool = fluid.layers.pool2d(input=input, - pool_size=2, - pool_stride=2, - pool_padding=0, - pool_type='avg', - ceil_mode=True) - - conv = fluid.layers.conv2d(input=pool, - num_filters=num_filters, - filter_size=filter_size, - stride=1, - padding=(filter_size - 1) // 2, - groups=groups, - act=None, - param_attr=ParamAttr(name=name + "_weights", - learning_rate=lr_mult), - bias_attr=False) + pool = fluid.layers.pool2d( + input=input, + pool_size=2, + pool_stride=2, + pool_padding=0, + pool_type='avg', + ceil_mode=True) + + conv = fluid.layers.conv2d( + input=pool, + num_filters=num_filters, + filter_size=filter_size, + stride=1, + padding=(filter_size - 1) // 2, + groups=groups, + act=None, + param_attr=ParamAttr(name=name + "_weights", learning_rate=lr_mult), + bias_attr=False) if name == "conv1": bn_name = "bn_" + name else: @@ -296,24 +300,20 @@ class ResNet(): return fluid.layers.batch_norm( input=conv, act=act, - param_attr=ParamAttr(name=bn_name + '_scale', - learning_rate=lr_mult), + param_attr=ParamAttr( + name=bn_name + '_scale', learning_rate=lr_mult), bias_attr=ParamAttr(bn_name + '_offset', learning_rate=lr_mult), moving_mean_name=bn_name + '_mean', moving_variance_name=bn_name + '_variance') def shortcut(self, input, ch_out, stride, is_first, name): ch_in = input.shape[1] - print('shortcut:', stride, is_first, ch_in, ch_out) if ch_in != ch_out or stride != 1: if is_first or stride == 1: return self.conv_bn_layer(input, ch_out, 1, stride, name=name) else: - return self.conv_bn_layer_new(input, - ch_out, - 1, - stride, - name=name) + return self.conv_bn_layer_new( + input, ch_out, 1, stride, name=name) elif is_first: return self.conv_bn_layer(input, ch_out, 1, stride, name=name) else: @@ -326,59 +326,58 @@ class ResNet(): name, is_first=False, dilation=1): - conv0 = self.conv_bn_layer(input=input, - num_filters=num_filters, - filter_size=1, - dilation=1, - stride=1, - act='relu', - name=name + "_branch2a") + conv0 = self.conv_bn_layer( + input=input, + num_filters=num_filters, + filter_size=1, + dilation=1, + stride=1, + act='relu', + name=name + "_branch2a") if dilation > 1: conv0 = self.zero_padding(conv0, dilation) - conv1 = self.conv_bn_layer(input=conv0, - num_filters=num_filters, - filter_size=3, - dilation=dilation, - stride=stride, - act='relu', - name=name + "_branch2b") - conv2 = self.conv_bn_layer(input=conv1, - num_filters=num_filters * 4, - dilation=1, - filter_size=1, - act=None, - name=name + "_branch2c") - - short = self.shortcut(input, - num_filters * 4, - stride, - is_first=is_first, - name=name + "_branch1") - print(input.shape, short.shape, conv2.shape) - print(stride) - - return fluid.layers.elementwise_add(x=short, - y=conv2, - act='relu', - name=name + ".add.output.5") + conv1 = self.conv_bn_layer( + input=conv0, + num_filters=num_filters, + filter_size=3, + dilation=dilation, + stride=stride, + act='relu', + name=name + "_branch2b") + conv2 = self.conv_bn_layer( + input=conv1, + num_filters=num_filters * 4, + dilation=1, + filter_size=1, + act=None, + name=name + "_branch2c") + + short = self.shortcut( + input, + num_filters * 4, + stride, + is_first=is_first, + name=name + "_branch1") + + return fluid.layers.elementwise_add( + x=short, y=conv2, act='relu', name=name + ".add.output.5") def basic_block(self, input, num_filters, stride, is_first, name): - conv0 = self.conv_bn_layer(input=input, - num_filters=num_filters, - filter_size=3, - act='relu', - stride=stride, - name=name + "_branch2a") - conv1 = self.conv_bn_layer(input=conv0, - num_filters=num_filters, - filter_size=3, - act=None, - name=name + "_branch2b") - short = self.shortcut(input, - num_filters, - stride, - is_first, - name=name + "_branch1") + conv0 = self.conv_bn_layer( + input=input, + num_filters=num_filters, + filter_size=3, + act='relu', + stride=stride, + name=name + "_branch2a") + conv1 = self.conv_bn_layer( + input=conv0, + num_filters=num_filters, + filter_size=3, + act=None, + name=name + "_branch2b") + short = self.shortcut( + input, num_filters, stride, is_first, name=name + "_branch1") return fluid.layers.elementwise_add(x=short, y=conv1, act='relu') diff --git a/pdseg/reader.py b/pdseg/reader.py index 6fe395d5..a18ea831 100644 --- a/pdseg/reader.py +++ b/pdseg/reader.py @@ -318,6 +318,8 @@ class SegDataset(object): raise ValueError("Dataset mode={} Error!".format(mode)) # Normalize image + if cfg.AUG.TO_RGB: + img = img[..., ::-1] img = self.normalize_image(img) if ModelPhase.is_train(mode) or ModelPhase.is_eval(mode): diff --git a/pdseg/utils/config.py b/pdseg/utils/config.py index 9ba00e05..a139c0a3 100644 --- a/pdseg/utils/config.py +++ b/pdseg/utils/config.py @@ -117,6 +117,8 @@ cfg.AUG.RICH_CROP.CONTRAST_JITTER_RATIO = 0.5 cfg.AUG.RICH_CROP.BLUR = False # 图像启动模糊百分比，0-1 cfg.AUG.RICH_CROP.BLUR_RATIO = 0.1 +# 图像是否切换到rgb模式 +cfg.AUG.TO_RGB = True ########################### 训练配置 ########################################## # 模型保存路径 -- GitLab