PyTorch

Question

学习 PyTorch，我是从 Quickstart Tutorial 开始的。在 train() 方法中，我注意到 they don't print the training accuracy during the training session。仅打印训练损失。

来自 Keras，这对我来说很不寻常，因为当您调用 fit() 时会自动打印训练准确率。

所以，我决定像下面这样修改教程代码来打印训练精度：

def train(dataloader, model, optimizer, loss_fn):

  model.train()
  size = len(dataloader.dataset)
  num_batches = len(dataloader)

  training_loss = 0.0
  correct = 0.0

  for batch, (imgs, labels) in enumerate(dataloader):
    imgs = imgs.to(device=device)
    labels = labels.to(device=device)

    predictions = model(imgs)
    loss = loss_fn(predictions, labels)

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

    # accumulate the training loss - each batch's loss will be added to trainin_loss
    training_loss += loss.item()
    
    # determines the number of correct predictions
    correct += (predictions.argmax(1) == labels).type(torch.float).sum().item()
  
  # end of for loop - all batches are processed      

  # after all batches are processed, determine the average training loss
  training_loss = training_loss / num_batches
  # this would be the training accuracy: number of correct predictions / number of samples in dataset
  correct = correct / size

  print(f"{datetime.datetime.now()} Training Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {training_loss:>8f} \n")

这样可以吗？作为 PyTorch 的初学者，我想在开始训练我的神经网络之前确保它是正确的。

Answer 1

看起来一切正常。这样做应该不会影响训练。 loss.backward() 计算你的梯度，任何不连接的东西都不能改变它们。顺便说一下，只是运行培训，你不能破坏任何东西:)（但是。等你开始制造自动驾驶汽车。）。

我想，在 Keras/TensorFlow fit() 中不会自动计算 accuracy，您仍然必须指定此指标，例如当编译模型或作为fit()的参数，例如：

model.compile(optimizer='sgd',
              loss='mse',
              metrics=[tf.keras.metrics.Accuracy()])

PyTorch - 计算和打印快速入门教程的训练准确性

PyTorch - Computing and printing the training accuracy of the QuickStart Tutorial

python