Bug in UpSampling2dLayer，tf.shape(xxx) will get None axis #899
Description
New Issue Checklist
- I have read the Contribution Guidelines
- I searched for existing GitHub issues
Issue Description
When I use UpSampling2dLayer, the outputs shape is [None, None, None, number]
It should use self.inputs.shape instead of tf.shape(self.inputs).
Reproducible Code
- Which OS are you using ?
win10 - 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 ######
# ======================================================== #
import tensorflow as tf
import tensorlayer as tl
a=tf.placeholder(tf.float32, [None, 4, 4, 3])
b=tl.layers.InputLayer(a)
c=tl.layers.UpSampling2dLayer(b, (2,2))
print(c.outputs.shape)