Tensorflow-使用tf.contrib.layers.conv2d时，我可以设置权重和偏差的名称吗？

Question

Tensorflow version: 1.10.1

I want to transfer my learned weights and biases of the convolution layers in my pretrained network to a new network.

However, because I used conv2d api, the weights and biases in the checkpoint file are automatically named as Conv/weights , Conv/biases , Conv_1/weights , Conv_1/biases , Conv_2/weights , Conv_2/biases etc.

However, these names are not consistent with my variable name in my codes. For example, Conv/weights , Conv/biases belongs to a variable named C2 in my codes, so I want to name them as C2/weights , C2/biases .

I know for varibales defined by get_variable , I can set their names to whatever strings I want by my_varibale = tf.get_variable("whatever_name_I_want",shape,dtype,initializer) , where my_variable is named to "whatever_name_I_want" .

However, when it comes to my_layer = tf.contrib.layers.conv2d(params_blabla) (or the equivalent api in tf.nn or tf.layers ), I don't know how I can name my_layer .

So, is it possible to do this? And if possible, how?

Answer 1

For tf.layers.conv2d and tf.nn.conv2d you can pass an additional parameter called name .

Example:

my_conv1 = tf.layers.conv2D(...., name='my_conv1')
my_conv2 = tf.layers.conv2D(...., name='my_conv2 ')

For tf.contrib.layers.conv2d the parameter scope is used to namespace your layers.

Example:

with tf.name_scope('my_conv1') as scope:
    my_conv1 = tf.contrib.layers.conv2d(..., scope=scope) 

Result:

In all cases your weights and biases are named like for example my_conv1/weights and my_conv1/bias .