小编Mal*_*rec的帖子

在使用tf.layers中定义的层时,是否可以添加L2正则化？

在我看来,由于tf.layers是一个高级包装器,因此没有简单的方法来访问过滤器权重.

使用tf.nn.conv2d

regularizer = tf.contrib.layers.l2_regularizer(scale=0.1)

weights = tf.get_variable(
    name="weights",
    regularizer=regularizer
)

#Previous layers

...

#Second layer 
layer 2 = tf.nn.conv2d(
input,
weights,
[1,1,1,1],
[1,1,1,1])

#More layers
...

#Loss
loss = #some loss

reg_variables = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
reg_term = tf.contrib.layers.apply_regularization(regularizer, reg_variables)
loss += reg_term

现在用tf.layers.conv2d会是什么样子？

谢谢!

由于没有明确定义权重,我如何将它们传递给摘要编写器？

举个例子:

conv1 = tf.layers.conv2d(
    tf.reshape(X,[FLAGS.batch,3,160,320]),
    filters = 16,
    kernel_size = (8,8),
    strides=(4, 4),
    padding='same',
    kernel_initializer=tf.contrib.layers.xavier_initializer(),
    bias_initializer=tf.zeros_initializer(),
    kernel_regularizer=None,
    name = 'conv1',
    activation = tf.nn.elu
    )

=>

summarize_tensor(
    ??????
)

谢谢!