Jun-Yan Zhu comments

Results 321 comments of


                                            Jun-Yan Zhu

Mean class IoU of photo2label

See this [post](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/1003) for more details regarding photo2label evaluation.

torch installation issue to run train.lua

See this [post](https://github.com/BVLC/caffe/issues/5141) for a potential fix. If you have trouble with Torch, you can also try our PyTorch [version](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix).

How can i see the values, tf.log(predict_real + EPS) and tf.log(1 - predict_fake + EPS) ??

You posted it to the wrong repo.

Same output for all inputs with test.lua

Did you see the same phenomena during your training? Are you able to run the train/test code on the facade dataset without problems?

Same output for all inputs with test.lua

I recommend you try to run the code on facade dataset first, and also double-check if your generated training/val set is correct (/my/data/root/)

BCHW format

Thank Fei for the nice work. Do you have any update on BCHW support?

BCHW format

@fxia22 Thanks for your prompt response. Good luck with your NIPS submission.

BCHW format

Thanks a lot!

PSNR and UQI Performance of Pretrained Model

We didn't report PNSR and UQI in our original pix2pix paper. I recommend that you contact the authors of "The effect of loss function on conditional generative adversarial networks" for...

pix2pix: RuntimeError: Calculated padded input size per channel: (4 x 3). Kernel size: (4 x 4). Kernel size can't be greater than actual input size

Not completely sure. What is your crop_size? Sometimes people use a smaller crop_size, and this error might happen. Also, could you check if all the images in your dataset are...