Dongxu
Dongxu
Got the same problem on Ubuntu 16.04. Python 3.5. `python3 bm3d.py` gives ``` PSNR of noisy image: 8.778750540392096 PSNR of reconstructed image: 9.685388621312667 ```
> Hi, I'm confused about the new readme "complete pipeline" example. > > Why does it do `dataset.batched(16)`, then `wds.WebLoader(..., batch_size=8)`, then `.unbatched()`, then `.batched(12)`? It says, "batch in the...
Any update on this, pleaes?
> I have the same issue, but it didn't crash the program. Also I visualized the extracted tensor, it actually looks fine despite the very serious-looking warning message? Do you...
@Vancelot11: Thanks for your kind contribution. I scrolled through the commits and it seems to me that they might nicely complement the repo. However, I could not schedule well for...
Thanks for raising this. I will fix this up later accordingly,
Another common cause is your local copy of the dataset misses some video files. Do you use official WLASL release or download from somewhere? Note that re-distribution of WLASL is...
Thanks a lot for pointing this out. It seems the current repo indeed does not pass in the weight decay. This may be an issue during open-sourcing. We'll update the...
Hi @vateye, an easy fix would be to pass the weight_decay to the optimizer. We will resolve this issue in future releases but would expect some delay. Nice catch and...
Thanks for the kind suggestion. It will be nice to have better installation instructions. We have noted this down and try to support it in our future release.