dongheehand/DeblurGAN-tf

Set Batchsize to 16 ,an error occurred

Nakupenda-7 opened this issue · 1 comments

Set Batchsize to 16,ValueError: Dimensions must be equal, but are 8 and 16 for 'discriminator_2/sub_1' (op: 'Sub') with input shapes: [16,?,8,128], [16,128].I looked at the code carefully and couldn't figure out where the problem was?thank you!

If you change the 32-nd line in ops.py, it will be ok.
I will update my code soon. Thank you!

mean, variance = tf.nn.moments(x, axes = [1, 2], keep_dims = True)

("keep_dims = True" option is added)