def train(model):
best = [0] # 保存最好权重
net = model.train()
# 训练轮次
for epoch in range(cfg.epoch_number):
print(f"Epoch is [{epoch + 1}/{cfg.epoch_number}]")
if epoch % 50 == 0 and epoch != 0:
for group in optimizer.param_groups:
group['lr'] *= 0.5
train_loss = 0
train_acc = 0
train_miou = 0
train_class_acc = 0 # 类的准确率
for i, sample in enumerate(train_data):
img_data = Variable(sample['img'].to(device))
img_label = Variable(sample['label'].to(device))
out = net(img_data)
out = F.log_softmax(out, dim=1) # log_sogtmax作用：？
loss = criterion(out, img_label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss += loss.item()
# 评估
pre_label = out.max(dim=1)[1].data.cpu().numpy()
pre_label = [i for i in pre_label]
true_label = img_label.data.cpu().numpy()
true_label = [i for i in true_label]
# 混淆矩阵
eval_metric = eval_semantic_segmentation(pre_label, true_label)
train_acc += eval_metric['mean_class_accuracy']
train_miou += eval_metric['miou']
train_class_acc += eval_metric['class_accuracy']
print('|batch[{}/{}]|batch_loss {: .8f}|'.format(
i + 1, len(train_data), loss.item()))
metric_description = '|Train Acc|: {:.5f}|Train Mean IU|: {:.5f}\n|Train_class_acc|:{:}'.format(
train_acc / len(train_data),
train_miou / len(train_data),
train_class_acc / len(train_data),
)
print(metric_description)
evaluate(net)
if max(best) <= train_miou / len(train_data):
best.append(train_miou / len(train_data))
torch.save(net.state_dict(), '{}.pth'.format(epoch))
def train(model):
best = [0]
net = model.train()
# 训练轮次
for epoch in range(cfg.EPOCH_NUMBER):
print('Epoch is [{}/{}]'.format(epoch + 1, cfg.EPOCH_NUMBER))
if epoch % 50 == 0 and epoch != 0:
for group in optimizer.param_groups:
group['lr'] *= 0.5
train_loss = 0
train_acc = 0
train_miou = 0
train_class_acc = 0
# 训练批次
for i, sample in enumerate(train_data):
# 载入数据
img_data = Variable(sample['img'].to(device))
img_label = Variable(sample['label'].to(device))
# 训练
out = net(img_data)
out = F.log_softmax(out, dim=1)
loss = criterion(out, img_label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss += loss.item()
# 评估
pre_label = out.max(dim=1)[1].data.cpu().numpy()
pre_label = [i for i in pre_label]
true_label = img_label.data.cpu().numpy()
true_label = [i for i in true_label]
eval_metrix = eval_semantic_segmentation(pre_label, true_label)
train_acc += eval_metrix['mean_class_accuracy']
train_miou += eval_metrix['miou']
train_class_acc += eval_metrix['class_accuracy']
print('|batch[{}/{}]|batch_loss {: .8f}|'.format(i + 1, len(train_data), loss.item()))
metric_description = '|Train Acc|: {:.5f}|Train Mean IU|: {:.5f}\n|Train_class_acc|:{:}'.format(
train_acc / len(train_data),
train_miou / len(train_data),
train_class_acc / len(train_data),
)
print(metric_description)
if max(best) <= train_miou / len(train_data):
best.append(train_miou / len(train_data))
t.save(net.state_dict(), './Results/weights/FCN_weight/{}.pth'.format(epoch))
def train(model):
best = [0]
net = model.train()
# 训练轮次
for epoch in range(cfg.EPOCH_NUMBER):
print("Eopch is [{}/{}]".format(epoch + 1, cfg.EPOCH_NUMBER))
if epoch % 50 == 0 and epoch != 0:
for group in optimizer.param_groups:
group["lr"] *= 0.5
train_loss = 0
train_acc = 0
train_miou = 0
train_class_acc = 0
for i, sample in enumerate(train_data):
img_data = Variable(sample["img"].to(device))
img_label = Variable(sample["label"].to(device))
out = net(img_data)
out = F.log_softmax(out, dim=1)
loss = criterion(out, img_label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
train_loss += loss.item()
pre_label = out.max(dim=1)[1].data.cpu().numpy()
pre_label = [i for i in pre_label]
true_label = img_label.data.cpu().numpy()
true_label = [i for i in true_label]
eval_metric = eval_semantic_segmentation(pre_label, true_label)
train_acc += eval_metric["mean_class_accuracy"]
train_miou += eval_metric["miou"]
train_class_acc += eval_metric["class_accuracy"]
print('|batch[{}/{}]|batch_loss {:.8f}|'.format(
i + 1, len(train_data), loss.item()))
t.save(net.state_dict(), 'xxx.pth')
def evaluate(model):
net = model.eval()
eval_loss = 0
eval_acc = 0
eval_miou = 0
eval_class_acc = 0
prec_time = datetime.now()
for j, sample in enumerate(val_data):
valImg = Variable(sample['img'].to(device))
valLabel = Variable(sample['label'].long().to(device))
out = net(valImg)
out = F.log_softmax(out, dim=1)
loss = criterion(out, valLabel)
eval_loss = loss.item() + eval_loss
pre_label = out.max(dim=1)[1].data.cpu().numpy()
pre_label = [i for i in pre_label]
true_label = valLabel.data.cpu().numpy()
true_label = [i for i in true_label]
eval_metrics = eval_semantic_segmentation(pre_label, true_label)
eval_acc = eval_metrics['mean_class_accuracy'] + eval_acc
eval_miou = eval_metrics['miou'] + eval_miou
# eval_class_acc = eval_metrix['class_accuracy'] + eval_class_acc
cur_time = datetime.now()
h, remainder = divmod((cur_time - prec_time).seconds, 3600)
m, s = divmod(remainder, 60)
time_str = 'Time: {:.0f}:{:.0f}:{:.0f}'.format(h, m, s)
val_str = ('|Valid Loss|: {:.5f} \n|Valid Acc|: {:.5f} \n|Valid Mean IU|: {:.5f} \n|Valid Class Acc|:{:}'.format(
eval_loss / len(train_data),
eval_acc / len(val_data),
eval_miou / len(val_data),
eval_class_acc / len(val_data)))
print(val_str)
print(time_str)
train_mpa = 0
error = 0
for i, sample in enumerate(test_data):
data = Variable(sample['img']).to(device)
label = Variable(sample['label']).to(device)
out = net(data)
out = F.log_softmax(out, dim=1)
pre_label = out.max(dim=1)[1].data.cpu().numpy()
pre_label = [i for i in pre_label]
true_label = label.data.cpu().numpy()
true_label = [i for i in true_label]
eval_metrix = eval_semantic_segmentation(pre_label, true_label)
train_acc = eval_metrix['mean_class_accuracy'] + train_acc
train_miou = eval_metrix['miou'] + train_miou
train_mpa = eval_metrix['pixel_accuracy'] + train_mpa
if len(eval_metrix['class_accuracy']) < 12:
eval_metrix['class_accuracy'] = 0
train_class_acc = train_class_acc + eval_metrix['class_accuracy']
error += 1
else:
train_class_acc = train_class_acc + eval_metrix['class_accuracy']
print(eval_metrix['class_accuracy'], '================', i)
epoch_str = (
'test_acc :{:.5f} ,test_miou:{:.5f}, test_mpa:{:.5f}, test_class_acc :{:}'.
format(train_acc / (len(test_data) - error),