CycleGAN-keras

CycleGAN-keras copied to clipboard

isn't there freezing of the D weights in your implementation when training G , or am I missing it?

stormsson

Dimensions error

2

ValueError: Dimensions must be equal, but are 3 and 4 for 'gen_A/instance_normalization2d_21/mul' (op: 'Mul') with input shapes: [1,3,1,1], [?,4,128,64].

jianhuaixie

Hi, Thanks for your valuable code. But I don't quite follow the logic for calculating the gan loss in the cyclegan.py. My understanding is the discriminator tries to tell the...

leoliuf

identity loss is not correct

1

I found in cyclegan.py, you are using opt.idloss as the loss weight of identity loss ``` if opt.idloss > 0: G_trainner = Model([real_A, real_B], [dis_fake_B, dis_fake_A, rec_A, rec_B, fake_B, fake_A])...

Trueyellow

array dimension not consistent error

1

this project is great, i just search for a CycleGAN implemented in keras, when i run the demo, i encounter a error "expected input_3 to have shape (None, 3, 128,...

qigangliu