CycleGAN

CycleGAN copied to clipboard

Testing on training data?

1

Hello, I don't see any use of the files under testA or testB in your code, are you testing the model on training data? thanks!

albertoandreottiATgmail

I think there are some problems in your function input_read() in main.py.

6

I think there are some problems in your function input_read() in main.py. Shouldn't we add code such like "while not coord.should_stop():" to make that the variable image_file_A always get images...

anqier0468

hi, i ran the model for 100 epochs ,but the result is not good like your ,it very poorly,code no changed

7

can you give me a suggestion

debin168

I'm confused about a question, Does the size of **pool_size** matter? If I set it bigger, will it learn better?

IronLavender

**fake_pool[random_id] = fake** --- what does use for in dis code? coz it return temp def fake_image_pool(self, num_fakes, fake, fake_pool): ''' dis function saves teh generated image to corresponding pool...

nalibjchn

I run this code on tensorflow 1.13.1. i found the error of image_tensor.size() and i change size() into size.

skconan

int object is not callable.

1

Hello, i am having tensorflow version 1.11.0 i had issue on initialize varaible but solved that issue by modifing to this (tf.global_variables_initializer(), tf.local_variables_initializer()), earlier it had only global initializer. After...

xyzdcgan

I’m puzzled since your already use a 70X70 patch discriminator in gen_discriminator but you still use random crop to build another “patch discriminator ”. I guess 70X70 is the size...

baldFemale

1. changed size into size(); 2. add initialization of local variables. 3. change code style.

ghost

I'm using TensorFlow of version 1.10.0. I need to do the following change in file `main.py` to run this code: 1. Change `size()` into `size` on line 99 & 104;...

ghost