1

我需要使用 Tensorflow/Keras 创建一个自定义训练循环（因为我想拥有多个优化器并告诉每个优化器应该处理哪些权重）。

尽管这个教程和那个教程对这个问题也很清楚，但他们忽略了一个非常重要的点：我如何预测训练阶段以及如何预测验证阶段？

假设我的模型有Dropout层或BatchNormalization层。无论是在训练还是在验证中，它们肯定以完全不同的方式工作。

我如何调整这些教程？这是一个虚拟示例（可能包含一两段伪代码）：

# Iterate over epochs.
for epoch in range(3):


    # Iterate over the batches of the dataset.
    for step, (x_batch_train, y_batch_train) in enumerate(train_dataset):
        with tf.GradientTape() as tape:

            #model with two outputs
            #IMPORTANT: must be in training phase (use dropouts, calculate batch statistics)
            logits1, logits2 = model(x_batch_train) #must be "training"

            loss_value1 = loss_fn1(y_batch_train[0], logits1)
            loss_value2 = loss_fn2(y_batch_train[1], logits2)

            grads1 = tape.gradient(loss_value1, model.trainable_weights[selection1])    
            grads2 = tape.gradient(loss_value2, model.trainable_weights[selection2])

            optimizer1.apply_gradients(zip(grads1, model.trainable_weights[selection1]))
            optimizer2.apply_gradients(zip(grads2, model.trainable_weights[selection2]))



    # Run a validation loop at the end of each epoch.
    for x_batch_val, y_batch_val in val_dataset:

        ##Important: must be validation phase
            #dropouts are off: calculate all neurons and divide value    
            #batch norms use previously calculated statistics    
        val_logits1, val_logits2 = model(x_batch_val)

        #.... do the evaluations
4

1 回答 1

2

我认为你可以training在调用 a 时传递一个参数tf.keras.Model，它将被传递给层：

# On training
logits1, logits2 = model(x_batch_train, training=True)
# On evaluation
val_logits1, val_logits2 = model(x_batch_val, training=False)
于 2019-09-19T13:47:10.873 回答