tf.AUTO_REUSE work with tf.layers.conv2d

[raytroop]

In 'Scopes and when to use them` section

with tf.variable_scope("scope", reuse=tf.AUTO_REUSE):
  features1 = tf.layers.conv2d(image1, filters=32, kernel_size=3)
  features2 = tf.layers.conv2d(image2, filters=32, kernel_size=3)

The above conv2d layer won't share weights, it seems that we have to explicitly specify name attribute of tf.layers.conv2d to share weights like,

with tf.variable_scope("scope", reuse=tf.AUTO_REUSE):
  features1 = tf.layers.conv2d(image1, filters=32, kernel_size=3, name='conv2d')
  features2 = tf.layers.conv2d(image2, filters=32, kernel_size=3, name='conv2d')

tf.version = 1.8.0

Thanks

[vahidk]

Thanks for finding this. Fixed.

Note that the reason this doesn't work is because of the counter in the variable_scope. The following should work:

with tf.variable_scope("scope", reuse=tf.AUTO_REUSE):
  features1 = tf.layers.conv2d(image1, filters=32, kernel_size=3)
  
with tf.variable_scope("scope", reuse=tf.AUTO_REUSE):
  features2 = tf.layers.conv2d(image2, filters=32, kernel_size=3)