zyfsa

hi, why I should be trained with OS=16, and only inferenced with OS=8? can not be trained in os=8?

hello, I also want to train the model on our own dataset. how to make the model can work on the image with different H,W,like(384,512,3). Now, the code only handle...

I also have the confusion. the goal of compute_bn_statistics.py is? when I test one image, why do not I fix the mean and the var gained in the training phase.

@cheer00 hello, I advise you load the imagenet-vgg-f.mat in matlab, and analyze it. If you also are puzzled,you can my watch my repository (cvpr2108-SSAH). I follow this work and have...

@1453183774 ,hi,I am regret to reply you now. when I download this VGG.mat(it is different with the authors),I open it with matlab, then, use this replace the authors code. I...

sorry to hear it. I can not meet this problem.you can check the version of software or use the original code of authors. Try it

@asiandragon my gpu is 1080Ti, training is quick. If you use the K80, it will relatively slow. Besides, I advise you try different training order. or lastly, reload the per-trained...

@asiandragon the first question, you are right. the second problem, too many epochs are useless. i run 60 epochs,then stop it, the time is about 12 hours.you can try it.

@asiandragon I think you are right. So I reload the pre-trained weights in checkpoints, only train the Generator. This brings some improvement. Besides, Training has a certain randomness. you can...

@asiandragon namely, I do not train the discriminator, only train the lab_net, img_net, text_net