图像分割实战-系列教程4：unet医学细胞分割实战2（医学数据集、图像分割、语义分割、unet网络、代码逐行解读）
图像分割实战-系列教程 总目录
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
上篇内容：
unet医学细胞分割实战1
下篇内容：
3、指定训练参数
"""
指定参数：
--dataset dsb2018_96
--arch NestedUNet
"""
指定数据集，指定网络架构后执行训练
4、训练函数
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)])
5、主函数
5.1 读取配置文件
def main():
config = vars(parse_args())
if config['name'] is None:
if config['deep_supervision']:
config['name'] = '%s_%s_wDS' % (config['dataset'], config['arch'])
else:
config['name'] = '%s_%s_woDS' % (config['dataset'], config['arch'])
os.makedirs('models/%s' % config['name'], exist_ok=True)
print('-' * 20)
for key in config:
print('%s: %s' % (key, config[key]))
print('-' * 20)
with open('models/%s/config.yml' % config['name'], 'w') as f:
yaml.dump(config, f)
5.2 损失函数
# define loss function (criterion)
if config['loss'] == 'BCEWithLogitsLoss':
criterion = nn.BCEWithLogitsLoss().cuda()#WithLogits 就是先将输出结果经过sigmoid再交叉熵
else:
criterion = losses.__dict__[config['loss']]().cuda()
cudnn.benchmark = True
# create model
print("=> creating model %s" % config['arch'])
model = archs.__dict__[config['arch']](config['num_classes'],
config['input_channels'],
config['deep_supervision'])
model = model.cuda()
params = filter(lambda p: p.requires_grad, model.parameters())
if config['optimizer'] == 'Adam':
optimizer = optim.Adam(
params, lr=config['lr'], weight_decay=config['weight_decay'])
elif config['optimizer'] == 'SGD':
optimizer = optim.SGD(params, lr=config['lr'], momentum=config['momentum'],
nesterov=config['nesterov'], weight_decay=config['weight_decay'])
else:
raise NotImplementedError
if config['scheduler'] == 'CosineAnnealingLR':
scheduler = lr_scheduler.CosineAnnealingLR(
optimizer, T_max=config['epochs'], eta_min=config['min_lr'])
elif config['scheduler'] == 'ReduceLROnPlateau':
scheduler = lr_scheduler.ReduceLROnPlateau(optimizer, factor=config['factor'], patience=config['patience'],
verbose=1, min_lr=config['min_lr'])
elif config['scheduler'] == 'MultiStepLR':
scheduler = lr_scheduler.MultiStepLR(optimizer, milestones=[int(e) for e in config['milestones'].split(',')], gamma=config['gamma'])
elif config['scheduler'] == 'ConstantLR':
scheduler = None
else:
raise NotImplementedError
# Data loading code
img_ids = glob(os.path.join('inputs', config['dataset'], 'images', '*' + config['img_ext']))
img_ids = [os.path.splitext(os.path.basename(p))[0] for p in img_ids]
train_img_ids, val_img_ids = train_test_split(img_ids, test_size=0.2, random_state=41)
5.3 数据集制作
#数据增强：
train_transform = Compose([
transforms.RandomRotate90(),
transforms.Flip(),
OneOf([
transforms.HueSaturationValue(),
transforms.RandomBrightness(),
transforms.RandomContrast(),
], p=1),#按照归一化的概率选择执行哪一个
transforms.Resize(config['input_h'], config['input_w']),
transforms.Normalize(),
])
val_transform = Compose([
transforms.Resize(config['input_h'], config['input_w']),
transforms.Normalize(),
])
train_dataset = Dataset(
img_ids=train_img_ids,
img_dir=os.path.join('inputs', config['dataset'], 'images'),
mask_dir=os.path.join('inputs', config['dataset'], 'masks'),
img_ext=config['img_ext'],
mask_ext=config['mask_ext'],
num_classes=config['num_classes'],
transform=train_transform)
val_dataset = Dataset(
img_ids=val_img_ids,
img_dir=os.path.join('inputs', config['dataset'], 'images'),
mask_dir=os.path.join('inputs', config['dataset'], 'masks'),
img_ext=config['img_ext'],
mask_ext=config['mask_ext'],
num_classes=config['num_classes'],
transform=val_transform)
train_loader = torch.utils.data.DataLoader(
train_dataset,
batch_size=config['batch_size'],
shuffle=True,
num_workers=config['num_workers'],
drop_last=True)#不能整除的batch是否就不要了
val_loader = torch.utils.data.DataLoader(
val_dataset,
batch_size=config['batch_size'],
shuffle=False,
num_workers=config['num_workers'],
drop_last=False)
log = OrderedDict([
('epoch', []),
('lr', []),
('loss', []),
('iou', []),
('val_loss', []),
('val_iou', []),
])
5.4 迭代训练
best_iou = 0
trigger = 0
for epoch in range(config['epochs']):
print('Epoch [%d/%d]' % (epoch, config['epochs']))
# train for one epoch
train_log = train(config, train_loader, model, criterion, optimizer)
# evaluate on validation set
val_log = validate(config, val_loader, model, criterion)
if config['scheduler'] == 'CosineAnnealingLR':
scheduler.step()
elif config['scheduler'] == 'ReduceLROnPlateau':
scheduler.step(val_log['loss'])
print('loss %.4f - iou %.4f - val_loss %.4f - val_iou %.4f'
% (train_log['loss'], train_log['iou'], val_log['loss'], val_log['iou']))
log['epoch'].append(epoch)
log['lr'].append(config['lr'])
log['loss'].append(train_log['loss'])
log['iou'].append(train_log['iou'])
log['val_loss'].append(val_log['loss'])
log['val_iou'].append(val_log['iou'])
pd.DataFrame(log).to_csv('models/%s/log.csv' %
config['name'], index=False)
trigger += 1
if val_log['iou'] > best_iou:
torch.save(model.state_dict(), 'models/%s/model.pth' %
config['name'])
best_iou = val_log['iou']
print("=> saved best model")
trigger = 0
# early stopping
if config['early_stopping'] >= 0 and trigger >= config['early_stopping']:
print("=> early stopping")
break
torch.cuda.empty_cache()