Problem with using LaylerNorm in tensorlayer 2

[mrgreen3325]

New Issue Checklist

• [ ] I have read the Contribution Guidelines
• [ ] I searched for existing GitHub issues

Issue Description

[INSERT DESCRIPTION OF THE PROBLEM]

Reproducible Code

• Which OS are you using ?
• Please provide a reproducible code of your issue. Without any reproducible code, you will probably not receive any help.

[INSERT CODE HERE]

# ======================================================== #
###### THIS CODE IS AN EXAMPLE, REPLACE WITH YOUR OWN ######
# ======================================================== #
nn = Conv2d(64, (3, 3), (1, 1), padding='SAME', W_init=w_init, b_init=None)(n)
nn = LayerNorm(act=tf.nn.relu)(nn)

# ======================================================== #
###### THIS CODE IS AN EXAMPLE, REPLACE WITH YOUR OWN ######
# ======================================================== #

Error: tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [1,1,1,8] vs. [1,1,1,64] [Op:Mul]

The original code is using the batchnorm2d with batch_size = 8. And I wanna change it to see the different. However, the program report with that error. Is that I use it unproperly? Thanks for help.

[Laicheng0830]

You may need to set the parameters begin_norm_axis=0 nn = Conv2d(64, (3, 3), (1, 1), padding='SAME', W_init=w_init, b_init=None)(n) nn = LayerNorm(begin_norm_axis=-1, act=tf.nn.relu)(nn)

[mrgreen3325]

You may need to set the parameters begin_norm_axis=-1 nn = Conv2d(64, (3, 3), (1, 1), padding='SAME', W_init=w_init, b_init=None)(n) nn = LayerNorm(begin_norm_axis=-1, act=tf.nn.relu)(nn)

Thanks laicheng. May I know what is begin_norm_axis this setting mean? Infact, the input batch of image is [8, 48, 48, 3] (the batch_size =8 ).

[Laicheng0830]

We wanted to compute mean and variance. norm_axes = range(begin_norm_axis, len(inputs_shape)-1) mean, var = tf.nn.moments(inputs, norm_axes, keepdims=True) for so-called "global normalization", used with convolutional filters with shape [batch, height, width, depth], pass norm_axes=[0, 1, 2]