有任何问题欢迎在下面留言
本篇文章的代码运行界面均在Pycharm中进行
本篇文章配套的代码资源已经上传
import torch
from torch import nn
__all__ = ['UNet', 'NestedUNet']
class VGGBlock(nn.Module):
def __init__(self, in_channels, middle_channels, out_channels):
super().__init__()
self.relu = nn.ReLU(inplace=True)
self.conv1 = nn.Conv2d(in_channels, middle_channels, 3, padding=1)
self.bn1 = nn.BatchNorm2d(middle_channels)
self.conv2 = nn.Conv2d(middle_channels, out_channels, 3, padding=1)
self.bn2 = nn.BatchNorm2d(out_channels)
def forward(self, x):
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
out = self.relu(out)
return out
class UNet(nn.Module):
def __init__(self, num_classes, input_channels=3, **kwargs):
super().__init__()
nb_filter = [32, 64, 128, 256, 512]
self.pool = nn.MaxPool2d(2, 2)
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
#scale_factor:放大的倍数 插值
self.conv0_0 = VGGBlock(input_channels, nb_filter[0], nb_filter[0])
self.conv1_0 = VGGBlock(nb_filter[0], nb_filter[1], nb_filter[1])
self.conv2_0 = VGGBlock(nb_filter[1], nb_filter[2], nb_filter[2])
self.conv3_0 = VGGBlock(nb_filter[2], nb_filter[3], nb_filter[3])
self.conv4_0 = VGGBlock(nb_filter[3], nb_filter[4], nb_filter[4])
self.conv3_1 = VGGBlock(nb_filter[3]+nb_filter[4], nb_filter[3], nb_filter[3])
self.conv2_2 = VGGBlock(nb_filter[2]+nb_filter[3], nb_filter[2], nb_filter[2])
self.conv1_3 = VGGBlock(nb_filter[1]+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv0_4 = VGGBlock(nb_filter[0]+nb_filter[1], nb_filter[0], nb_filter[0])
self.final = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
def forward(self, input):
x0_0 = self.conv0_0(input)
x1_0 = self.conv1_0(self.pool(x0_0))
x2_0 = self.conv2_0(self.pool(x1_0))
x3_0 = self.conv3_0(self.pool(x2_0))
x4_0 = self.conv4_0(self.pool(x3_0))
x3_1 = self.conv3_1(torch.cat([x3_0, self.up(x4_0)], 1))
x2_2 = self.conv2_2(torch.cat([x2_0, self.up(x3_1)], 1))
x1_3 = self.conv1_3(torch.cat([x1_0, self.up(x2_2)], 1))
x0_4 = self.conv0_4(torch.cat([x0_0, self.up(x1_3)], 1))
output = self.final(x0_4)
return output
class NestedUNet(nn.Module):
def __init__(self, num_classes, input_channels=3, deep_supervision=False, **kwargs):
super().__init__()
nb_filter = [32, 64, 128, 256, 512]
self.deep_supervision = deep_supervision
self.pool = nn.MaxPool2d(2, 2)
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
self.conv0_0 = VGGBlock(input_channels, nb_filter[0], nb_filter[0])
self.conv1_0 = VGGBlock(nb_filter[0], nb_filter[1], nb_filter[1])
self.conv2_0 = VGGBlock(nb_filter[1], nb_filter[2], nb_filter[2])
self.conv3_0 = VGGBlock(nb_filter[2], nb_filter[3], nb_filter[3])
self.conv4_0 = VGGBlock(nb_filter[3], nb_filter[4], nb_filter[4])
self.conv0_1 = VGGBlock(nb_filter[0]+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_1 = VGGBlock(nb_filter[1]+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv2_1 = VGGBlock(nb_filter[2]+nb_filter[3], nb_filter[2], nb_filter[2])
self.conv3_1 = VGGBlock(nb_filter[3]+nb_filter[4], nb_filter[3], nb_filter[3])
self.conv0_2 = VGGBlock(nb_filter[0]*2+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_2 = VGGBlock(nb_filter[1]*2+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv2_2 = VGGBlock(nb_filter[2]*2+nb_filter[3], nb_filter[2], nb_filter[2])
self.conv0_3 = VGGBlock(nb_filter[0]*3+nb_filter[1], nb_filter[0], nb_filter[0])
self.conv1_3 = VGGBlock(nb_filter[1]*3+nb_filter[2], nb_filter[1], nb_filter[1])
self.conv0_4 = VGGBlock(nb_filter[0]*4+nb_filter[1], nb_filter[0], nb_filter[0])
if self.deep_supervision:
self.final1 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final2 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final3 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
self.final4 = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
else:
self.final = nn.Conv2d(nb_filter[0], num_classes, kernel_size=1)
def forward(self, input):
print('input:',input.shape)
x0_0 = self.conv0_0(input)
print('x0_0:',x0_0.shape)
x1_0 = self.conv1_0(self.pool(x0_0))
print('x1_0:',x1_0.shape)
x0_1 = self.conv0_1(torch.cat([x0_0, self.up(x1_0)], 1))
print('x0_1:',x0_1.shape)
x2_0 = self.conv2_0(self.pool(x1_0))
print('x2_0:',x2_0.shape)
x1_1 = self.conv1_1(torch.cat([x1_0, self.up(x2_0)], 1))
print('x1_1:',x1_1.shape)
x0_2 = self.conv0_2(torch.cat([x0_0, x0_1, self.up(x1_1)], 1))
print('x0_2:',x0_2.shape)
x3_0 = self.conv3_0(self.pool(x2_0))
print('x3_0:',x3_0.shape)
x2_1 = self.conv2_1(torch.cat([x2_0, self.up(x3_0)], 1))
print('x2_1:',x2_1.shape)
x1_2 = self.conv1_2(torch.cat([x1_0, x1_1, self.up(x2_1)], 1))
print('x1_2:',x1_2.shape)
x0_3 = self.conv0_3(torch.cat([x0_0, x0_1, x0_2, self.up(x1_2)], 1))
print('x0_3:',x0_3.shape)
x4_0 = self.conv4_0(self.pool(x3_0))
print('x4_0:',x4_0.shape)
x3_1 = self.conv3_1(torch.cat([x3_0, self.up(x4_0)], 1))
print('x3_1:',x3_1.shape)
x2_2 = self.conv2_2(torch.cat([x2_0, x2_1, self.up(x3_1)], 1))
print('x2_2:',x2_2.shape)
x1_3 = self.conv1_3(torch.cat([x1_0, x1_1, x1_2, self.up(x2_2)], 1))
print('x1_3:',x1_3.shape)
x0_4 = self.conv0_4(torch.cat([x0_0, x0_1, x0_2, x0_3, self.up(x1_3)], 1))
print('x0_4:',x0_4.shape)
if self.deep_supervision:
output1 = self.final1(x0_1)
output2 = self.final2(x0_2)
output3 = self.final3(x0_3)
output4 = self.final4(x0_4)
return [output1, output2, output3, output4]
else:
output = self.final(x0_4)
return output
import os
import cv2
import numpy as np
import torch
import torch.utils.data
class Dataset(torch.utils.data.Dataset):
def __init__(self, img_ids, img_dir, mask_dir, img_ext, mask_ext, num_classes, transform=None):
"""
Args:
img_ids (list): Image ids.
img_dir: Image file directory.
mask_dir: Mask file directory.
img_ext (str): Image file extension.
mask_ext (str): Mask file extension.
num_classes (int): Number of classes.
transform (Compose, optional): Compose transforms of albumentations. Defaults to None.
Note:
Make sure to put the files as the following structure:
<dataset name>
├── images
| ├── 0a7e06.jpg
│ ├── 0aab0a.jpg
│ ├── 0b1761.jpg
│ ├── ...
|
└── masks
├── 0
| ├── 0a7e06.png
| ├── 0aab0a.png
| ├── 0b1761.png
| ├── ...
|
├── 1
| ├── 0a7e06.png
| ├── 0aab0a.png
| ├── 0b1761.png
| ├── ...
...
"""
self.img_ids = img_ids
self.img_dir = img_dir
self.mask_dir = mask_dir
self.img_ext = img_ext
self.mask_ext = mask_ext
self.num_classes = num_classes
self.transform = transform
def __len__(self):
return len(self.img_ids)
def __getitem__(self, idx):
img_id = self.img_ids[idx]
img = cv2.imread(os.path.join(self.img_dir, img_id + self.img_ext))
mask = []
for i in range(self.num_classes):
mask.append(cv2.imread(os.path.join(self.mask_dir, str(i),
img_id + self.mask_ext), cv2.IMREAD_GRAYSCALE)[..., None])
mask = np.dstack(mask)
if self.transform is not None:
augmented = self.transform(image=img, mask=mask)#这个包比较方便，能把mask也一并做掉
img = augmented['image']#参考https://github.com/albumentations-team/albumentations
mask = augmented['mask']
img = img.astype('float32') / 255
img = img.transpose(2, 0, 1)
mask = mask.astype('float32') / 255
mask = mask.transpose(2, 0, 1)
return img, mask, {'img_id': img_id}
def train(config, train_loader, model, criterion, optimizer):
avg_meters = {'loss': AverageMeter(), 'iou': AverageMeter()}
model.train()
pbar = tqdm(total=len(train_loader))
for input, target, _ in train_loader:
input = input.cuda()
target = target.cuda()
# compute output
if config['deep_supervision']:
outputs = model(input)
loss = 0
for output in outputs:
loss += criterion(output, target)
loss /= len(outputs)
iou = iou_score(outputs[-1], target)
else:
output = model(input)
loss = criterion(output, target)
iou = iou_score(output, target)
# compute gradient and do optimizing step
optimizer.zero_grad()
loss.backward()
optimizer.step()
avg_meters['loss'].update(loss.item(), input.size(0))
avg_meters['iou'].update(iou, input.size(0))
postfix = OrderedDict([
('loss', avg_meters['loss'].avg),
('iou', avg_meters['iou'].avg),
])
pbar.set_postfix(postfix)
pbar.update(1)
pbar.close()
return OrderedDict([('loss', avg_meters['loss'].avg),
('iou', avg_meters['iou'].avg)])
def validate(config, val_loader, model, criterion):
avg_meters = {'loss': AverageMeter(),
'iou': AverageMeter()}
# switch to evaluate mode
model.eval()
with torch.no_grad():
pbar = tqdm(total=len(val_loader))
for input, target, _ in val_loader:
input = input.cuda()
target = target.cuda()
# compute output
if config['deep_supervision']:
outputs = model(input)
loss = 0
for output in outputs:
loss += criterion(output, target)
loss /= len(outputs)
iou = iou_score(outputs[-1], target)
else:
output = model(input)
loss = criterion(output, target)
iou = iou_score(output, target)
avg_meters['loss'].update(loss.item(), input.size(0))
avg_meters['iou'].update(iou, input.size(0))
postfix = OrderedDict([
('loss', avg_meters['loss'].avg),
('iou', avg_meters['iou'].avg),
])
pbar.set_postfix(postfix)
pbar.update(1)
pbar.close()
return OrderedDict([('loss', avg_meters['loss'].avg),
('iou', avg_meters['iou'].avg)])