直接在tensorflow中的辍学层：如何训练？

Question

在Keras中创建了模型之后，我想得到渐变，并使用tf.train.AdamOptimizer公司班级。但是，由于我使用的是一个退出层，我不知道如何告诉模型它是否处于训练模式。不接受training关键字。代码如下：

    net_input = Input(shape=(1,))
    net_1 = Dense(50)
    net_2 = ReLU()
    net_3 = Dropout(0.5)
    net = Model(net_input, net_3(net_2(net_1(net_input))))

    #mycost = ...

    optimizer = tf.train.AdamOptimizer()
    gradients = optimizer.compute_gradients(mycost, var_list=[net.trainable_weights])
    # perform some operations on the gradients
    # gradients = ...
    trainstep = optimizer.apply_gradients(gradients)

我得到了相同的行为有和没有辍学层，即使有辍学rate=1。如何解决这个问题？在

Answer 1

Keras层继承自tf.keras.层.层类。kerasapi用model.fit在内部处理这个问题。如果Keras Dropout与纯TensorFlow训练循环一起使用，它在其调用函数中支持训练参数。在

所以你可以用

dropout = tf.keras.layers.Dropout(rate, noise_shape, seed)(prev_layer, training=is_training)

来自官方的TF文件

Note: - The following optional keyword arguments are reserved for specific uses: * training: Boolean scalar tensor of Python boolean indicating whether the call is meant for training or inference. * mask: Boolean input mask. - If the layer's call method takes a mask argument (as some Keras layers do), its default value will be set to the mask generated for inputs by the previous layer (if input did come from a layer that generated a corresponding mask, i.e. if it came from a Keras layer with masking support. https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dropout#call