在tensorflow中使用metric.Mean()

Question

我正在使用Google Colabs中的tensorflow教程,并按照以下链接中的教程指定运行所有内容:

https://www.tensorflow.org/tutorials/eager/custom_training_walkthrough

我正在运行以下代码:

## Note: Rerunning this cell uses the same model variables

# keep results for plotting
train_loss_results = []
train_accuracy_results = []

num_epochs = 201

for epoch in range(num_epochs):
  epoch_loss_avg = tf.metrics.Mean()
  epoch_accuracy = tf.metrics.Accuracy()

  # Training loop - using batches of 32
  for x, y in train_dataset:
    # Optimize the model
    loss_value, grads = grad(model, x, y)
    optimizer.apply_gradients(zip(grads, model.variables),
                              global_step)

    # Track progress
    epoch_loss_avg(loss_value)  # add current batch loss
    # compare predicted label to actual label
    epoch_accuracy(tf.argmax(model(x), axis=1, output_type=tf.int32), y)

  # end epoch
  train_loss_results.append(epoch_loss_avg.result())
  train_accuracy_results.append(epoch_accuracy.result())

  if epoch % 50 == 0:
    print("Epoch {:03d}: Loss: {:.3f}, Accuracy: {:.3%}".format(epoch,
                                                                epoch_loss_avg.result(),
                                                                epoch_accuracy.result()))

但是当我运行它时,我收到以下错误:

AttributeError: module 'tensorflow._api.v1.metrics' has no attribute 'Mean'

根据我的理解,他们在代码中尝试将tf.metrics.Mean()的函数分配给epoch_loss_avg,然后在epoch_loss_avg(loss_value)中进一步应用它.所以我想也许自从本教程编写以来,Tensorflow中的某些内容已经发生了变化,所以我尝试将其重写如下:

## Note: Rerunning this cell uses the same model variables

# Keep results for plotting
train_loss_results = []
train_accuracy_result = []

num_epochs = 201

for epoch in range(num_epochs):
  #epoch_loss_avg = tf.metrics.Mean()
  #epoch_accuracy = tf.metrics.Accuracy()

  # Training loop - using batches of 32
  for x, y in train_dataset:
    # Optimize the model
    loss_value, grads = grad(model, x, y)
    optimizer.apply_gradients(zip(grads, model.variables),
                             global_step)

    # Track progress
    mean_temp = tf.metrics.mean(loss_value) # Add current batch loss
    # Compare the predicted label to actual label
    acc_temp = tf.metrics.accuracy(tf.argmax(model(x), axis = 1, output_type = tf.int32), y)

  # End epoch
  train_loss_results.append(mean_temp)
  train_accuracy_results.append(acc_temp)

  if epoch % 50 == 0:
    print("Epoch {:03d}: Loss: {:,3f}, Accuracy: {:.3f}".format(epoch,
                                                               epoch_loss_avg.result(),
                                                               epoch_accuracy.result()))

函数只是直接运行,但现在我收到另一条错误消息:

RuntimeError: tf.metrics.mean is not supported when eager execution is enabled.

所以我的问题是,是否有另一种方法来编写这个以获得相同的结果,并且我对正在发生的事情的解释是否正确,如果不是正在发生的事情？

谢谢

Answer 1

要使用Eager Execution,您需要更改tf.metrics.Mean并tf.metrics.Accuracy:

epoch_loss_avg = tf.contrib.eager.metrics.Mean()
epoch_accuracy = tf.contrib.eager.metrics.Accuracy()

还有tf.Variable:

global_step = tf.contrib.eager.Variable(0)

根据我的理解,他们在代码中尝试将tf.metrics.Mean()的函数分配给epoch_loss_avg,然后在epoch_loss_avg(loss_value)中进一步应用它.

是的,在线,epoch_loss_avg = tf.metrics.Mean()他们创建了计算平均值的操作,然后他们累积了批量的损失epoch_loss_avg(loss_value).因此,在时代结束时,考虑到数据集中的所有批次,我们将有平均损失,然后导致时期(线epoch_loss_avg.result())的损失.

关于第二个错误:tf.metrics.mean提出了RuntimeError如果急于执行启用,因为你看到的.你需要tf.contrib.eager.metrics改用.