search

dongheehand / DeblurGAN-tf

Tensorflow implementation of DeblurGAN(Blind Motion Deblurring Using Conditional Adversarial Networks)
80 stars 24 forks source link

Set Batchsize to 16 ，an error occurred #12

Closed Nakupenda-7 closed 4 years ago

Nakupenda-7 commented 4 years ago

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！

dongheehand commented 4 years ago

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)