magic_frog
Linked to this issue. #15
> Thank you for the submission! how is it going?
`leetcode user -c` should work. You should manually copy the total cookie string instead of relying on the automatic process. For those entrants, I have a Chinese article to illustrate...
> There will be multiple/redundant outputs. It does not affect training. This is a WIP. I suggest we use `will be fixed in the future` instead of `WIP`. Many probably...
> @NanoCode012 does that make sense about the global vs local batch sizes being passed to test.py? @glenn-jocher After my fix, the training.py would run parallel test and global_batch_size would...
> hi! @glenn-jocher for multi-gpu training, if using smaller batch size than 64, could you suggest the hyperparameter to adjust like the learning rate? Internally, batch size is kept at...
> The 1x kernel is the blur kernel, NOT the SR kernel. Hence, not related to this work. Sorry Interesting topic. I am wondering > the true SR-kernel is the...
> We had a thought to apply KernelGAN for deblurring but it was not straight forward as you say Yeah. You will get an impluse filter in the end.
啊 为啥 仓库主应该不懒才对 他都回我了
打开Github Page https://scutan90.github.io/DeepLearning-500-questions