在 keras 优化器中获取 epoch

Question

我正在为 keras 编写一个自定义优化器，并且我需要在每个 epoch 之后更新一个变量，但是 keras 似乎只允许我在每次训练迭代之后（基本上在每批之后）更新它。是否有任何默认方法可以做到这一点，所以我不必手动指定优化器的批量大小？

Answer 1

在 Keras 中，纪元在 Model.fit() 中存储和迭代，因此您需要编写自定义训练循环并在外循环结束时编写逻辑。

代码来自：https://keras.io/guides/writing_a_training_loop_from_scratch/

# Given a callable model, inputs, outputs, and a learning rate...
epochs = 2
for epoch in range(epochs):
    print("\nStart of epoch %d" % (epoch,))

    # Iterate over the batches of the dataset.
    for step, (x_batch_train, y_batch_train) in enumerate(train_dataset):

        # Open a GradientTape to record the operations run
        # during the forward pass, which enables auto-differentiation.
        with tf.GradientTape() as tape:

            # Run the forward pass of the layer.
            # The operations that the layer applies
            # to its inputs are going to be recorded
            # on the GradientTape.
            logits = model(x_batch_train, training=True)  # Logits for this minibatch

            # Compute the loss value for this minibatch.
            loss_value = loss_fn(y_batch_train, logits)

        # Use the gradient tape to automatically retrieve
        # the gradients of the trainable variables with respect to the loss.
        grads = tape.gradient(loss_value, model.trainable_weights)

        # Run one step of gradient descent by updating
        # the value of the variables to minimize the loss.
        optimizer.apply_gradients(zip(grads, model.trainable_weights))
  
        #Update your variable