Skip to content

M
mindspore

magicwindyyd / mindspore
与 Fork 源项目一致

Fork自 MindSpore / mindspore

通知 1
Star 1
Fork 0
M
mindspore
提交 2065383e 编写于 作者: Y yangyongjie
浏览文件
操作

pylint fix

上级 ee2efd35
隐藏空白更改
内联 并排
Showing with 54 addition and 51 deletion
model_zoo/deeplabv3/evaluation.py
浏览文件 @ 2065383e
......@@ -22,6 +22,8 @@ from src.losses import OhemLoss
from src.miou_precision import MiouPrecision
from src.deeplabv3 import deeplabv3_resnet50
from src.config import config
parser = argparse.ArgumentParser(description="Deeplabv3 evaluation")
parser.add_argument('--epoch_size', type=int, default=2, help='Epoch size.')
parser.add_argument("--device_id", type=int, default=0, help="Device id, default is 0.")
......@@ -32,14 +34,16 @@ parser.add_argument('--checkpoint_url', default=None, help='Checkpoint path')
args_opt = parser.parse_args()
context.set_context(mode=context.GRAPH_MODE, device_target="Ascend", device_id=args_opt.device_id)
print(args_opt)
if __name__ == "__main__":
args_opt.crop_size = config.crop_size
args_opt.base_size = config.crop_size
eval_dataset = create_dataset(args_opt, args_opt.data_url, args_opt.epoch_size, args_opt.batch_size, usage="eval")
net = deeplabv3_resnet50(config.seg_num_classes, [args_opt.batch_size, 3, args_opt.crop_size, args_opt.crop_size],
infer_scale_sizes=config.eval_scales, atrous_rates=config.atrous_rates,
decoder_output_stride=config.decoder_output_stride, output_stride=config.output_stride,
fine_tune_batch_norm=config.fine_tune_batch_norm, image_pyramid=config.image_pyramid)
net = deeplabv3_resnet50(config.seg_num_classes, [args_opt.batch_size, 3, args_opt.crop_size, args_opt.crop_size],
infer_scale_sizes=config.eval_scales, atrous_rates=config.atrous_rates,
decoder_output_stride=config.decoder_output_stride, output_stride=config.output_stride,
fine_tune_batch_norm=config.fine_tune_batch_norm, image_pyramid=config.image_pyramid)
param_dict = load_checkpoint(args_opt.checkpoint_url)
load_param_into_net(net, param_dict)
mIou = MiouPrecision(config.seg_num_classes)
......@@ -47,4 +51,3 @@ if __name__ == "__main__":
loss = OhemLoss(config.seg_num_classes, config.ignore_label)
model = Model(net, loss, metrics=metrics)
model.eval(eval_dataset)
\ No newline at end of file
model_zoo/deeplabv3/src/backbone/resnet_deeplab.py
浏览文件 @ 2065383e
......@@ -93,31 +93,30 @@ def _stob_deep_conv_btos_bn_relu(in_channel,
def _stob_conv_btos_bn_relu(in_channel,
out_channel,
ksize,
space_to_batch_block_shape,
batch_to_space_block_shape,
paddings,
crops,
stride=1,
padding=0,
dilation=1,
pad_mode="pad",
use_batch_statistics=False):
out_channel,
ksize,
space_to_batch_block_shape,
batch_to_space_block_shape,
paddings,
crops,
stride=1,
padding=0,
dilation=1,
pad_mode="pad",
use_batch_statistics=False):
"""Get a spacetobatch -> conv2d -> batchnorm -> relu -> batchtospace layer"""
return nn.SequentialCell(
[SpaceToBatch(space_to_batch_block_shape,paddings),
nn.Conv2d(in_channel,
out_channel,
kernel_size=ksize,
stride=stride,
padding=padding,
dilation=dilation,
pad_mode=pad_mode),
BatchToSpace(batch_to_space_block_shape,crops),
nn.BatchNorm2d(out_channel,use_batch_statistics=use_batch_statistics),
nn.ReLU()]
)
return nn.SequentialCell([SpaceToBatch(space_to_batch_block_shape, paddings),
nn.Conv2d(in_channel,
out_channel,
kernel_size=ksize,
stride=stride,
padding=padding,
dilation=dilation,
pad_mode=pad_mode),
BatchToSpace(batch_to_space_block_shape, crops),
nn.BatchNorm2d(out_channel, use_batch_statistics=use_batch_statistics),
nn.ReLU()]
)
def _make_layer(block,
......@@ -206,6 +205,7 @@ class BatchToSpace(nn.Cell):
class _DepthwiseConv2dNative(nn.Cell):
"""Depthwise Conv2D Cell."""
def __init__(self,
in_channels,
channel_multiplier,
......@@ -242,6 +242,7 @@ class _DepthwiseConv2dNative(nn.Cell):
class DepthwiseConv2dNative(_DepthwiseConv2dNative):
"""Depthwise Conv2D Cell."""
def __init__(self,
in_channels,
channel_multiplier,
......@@ -315,31 +316,31 @@ class BottleneckV1(nn.Cell):
padding=1,
dilation=1,
use_batch_statistics=use_batch_statistics)
if use_batch_to_stob_and_btos == True:
if use_batch_to_stob_and_btos:
self.conv_bn2 = _stob_conv_btos_bn_relu(mid_channels,
mid_channels,
ksize=3,
stride=stride,
padding=0,
dilation=1,
space_to_batch_block_shape = 2,
batch_to_space_block_shape = 2,
paddings =[[2, 3], [2, 3]],
crops =[[0, 1], [0, 1]],
space_to_batch_block_shape=2,
batch_to_space_block_shape=2,
paddings=[[2, 3], [2, 3]],
crops=[[0, 1], [0, 1]],
pad_mode="valid",
use_batch_statistics=use_batch_statistics)
self.conv3 = nn.Conv2d(mid_channels,
out_channels,
kernel_size=1,
stride=1)
self.bn3 = nn.BatchNorm2d(out_channels,use_batch_statistics=use_batch_statistics)
self.bn3 = nn.BatchNorm2d(out_channels, use_batch_statistics=use_batch_statistics)
if in_channels != out_channels:
conv = nn.Conv2d(in_channels,
out_channels,
kernel_size=1,
stride=stride)
bn = nn.BatchNorm2d(out_channels,use_batch_statistics=use_batch_statistics)
bn = nn.BatchNorm2d(out_channels, use_batch_statistics=use_batch_statistics)
self.downsample = nn.SequentialCell([conv, bn])
else:
self.downsample = Subsample(stride)
......@@ -397,23 +398,23 @@ class BottleneckV2(nn.Cell):
stride=stride,
padding=0,
dilation=1,
space_to_batch_block_shape = 2,
batch_to_space_block_shape = 2,
paddings =[[2, 3], [2, 3]],
crops =[[0, 1], [0, 1]],
space_to_batch_block_shape=2,
batch_to_space_block_shape=2,
paddings=[[2, 3], [2, 3]],
crops=[[0, 1], [0, 1]],
pad_mode="valid",
use_batch_statistics=use_batch_statistics)
self.conv3 = nn.Conv2d(mid_channels,
out_channels,
kernel_size=1,
stride=1)
self.bn3 = nn.BatchNorm2d(out_channels,use_batch_statistics=use_batch_statistics)
self.bn3 = nn.BatchNorm2d(out_channels, use_batch_statistics=use_batch_statistics)
if in_channels != out_channels:
conv = nn.Conv2d(in_channels,
out_channels,
kernel_size=1,
stride=stride)
bn = nn.BatchNorm2d(out_channels,use_batch_statistics=use_batch_statistics)
bn = nn.BatchNorm2d(out_channels, use_batch_statistics=use_batch_statistics)
self.downsample = nn.SequentialCell([conv, bn])
else:
self.downsample = Subsample(stride)
......@@ -465,14 +466,14 @@ class BottleneckV3(nn.Cell):
out_channels,
kernel_size=1,
stride=1)
self.bn3 = nn.BatchNorm2d(out_channels,use_batch_statistics=use_batch_statistics)
self.bn3 = nn.BatchNorm2d(out_channels, use_batch_statistics=use_batch_statistics)
if in_channels != out_channels:
conv = nn.Conv2d(in_channels,
out_channels,
kernel_size=1,
stride=stride)
bn = nn.BatchNorm2d(out_channels,use_batch_statistics=use_batch_statistics)
bn = nn.BatchNorm2d(out_channels, use_batch_statistics=use_batch_statistics)
self.downsample = nn.SequentialCell([conv, bn])
else:
self.downsample = Subsample(stride)
......@@ -502,9 +503,8 @@ class ResNetV1(nn.Cell):
super(ResNetV1, self).__init__()
self.layer_root = nn.SequentialCell(
[RootBlockBeta(fine_tune_batch_norm),
nn.MaxPool2d(kernel_size=(3,3),
stride=(2,2),
#padding=1,
nn.MaxPool2d(kernel_size=(3, 3),
stride=(2, 2),
pad_mode='same')])
self.layer1_1 = BottleneckV1(128, 256, stride=1, use_batch_statistics=fine_tune_batch_norm)
self.layer1_2 = BottleneckV2(256, 256, stride=1, use_batch_statistics=fine_tune_batch_norm)
......@@ -519,7 +519,7 @@ class ResNetV1(nn.Cell):
self.layer3_4 = BottleneckV2(1024, 1024, stride=1, use_batch_statistics=fine_tune_batch_norm)
self.layer3_5 = BottleneckV2(1024, 1024, stride=1, use_batch_statistics=fine_tune_batch_norm)
self.layer3_6 = BottleneckV2(1024, 1024, stride=1, use_batch_statistics=fine_tune_batch_norm)
self.layer4_1 = BottleneckV1(1024, 2048, stride=1, use_batch_to_stob_and_btos=True,
use_batch_statistics=fine_tune_batch_norm)
self.layer4_2 = BottleneckV2(2048, 2048, stride=1, use_batch_to_stob_and_btos=True,
......@@ -542,7 +542,7 @@ class ResNetV1(nn.Cell):
x = self.layer3_4(x)
x = self.layer3_5(x)
x = self.layer3_6(x)
x = self.layer4_1(x)
x = self.layer4_2(x)
c5 = self.layer4_3(x)
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或