pytorch训练网络时的iter和epoch

Iter------一次迭代，是指一个min_batch的一次forward+backward

Epoch------迭代完所有的训练数据(1次)，称为一个epoch

# 训练网络
# 迭代epoch
for epoch in range(20):

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the input
        inputs, labels = data

        # zeros the paramster gradients
        optimizer.zero_grad()       # 

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)  # 计算loss
        loss.backward()     # loss 求导
        optimizer.step()    # 更新参数

        # print statistics
        running_loss += loss.item()  # tensor.item()  获取tensor的数值
        if i % 2000 == 1999:
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))  # 每2000次迭代，输出loss的平均值
            running_loss = 0.0

print('Finished Training')