eastchun

No, I didn't get the taichi512 dataset. The reason why I closed this issue was I was no longer interested in Taichi dataset. BTW, in order to prepare taichi 512...

If the bbox is smaller than 512x512, black color is painted for those missing areas ... It will hurt the quality anyway. In the worst case, you just identify those...

No, I didn't generate the taichi 512x512 dataset and I don't have it. On Sat, Jun 12, 2021 at 11:16 PM JialeTao ***@***.***> wrote: > If the bbox is smaller...

Default kernel initializer for tf.layer.conv2d is "glorot_uniform_initializer". Please refer to code lines '315 - 317' in : https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/variable_scope.py

I had the same problem and I delved into the code and found that the matting function in the line 214 in ./models/networks/generator.py is somehow disabled (I don't know why...

@erew123 I followed your instructions and successfully built and installed deepspeed 8.3 wheel on python 3.9 / windows 11. But, when I ran it, I got the following error message:...

Thanks @erew123 for quick reply. It appears that other people also mentioned deepspeed issue in Windows for 'gloo' supporting. Please refer to the following related links: https://github.com/microsoft/DeepSpeed/issues/1030#issue-873946980 https://github.com/oobabooga/text-generation-webui/issues/1225#issue-1669315797 https://github.com/pytorch/pytorch/issues/71049#issue-1096843011 Anyway,...

@erew123 In order to run deepspeed in Windows environment with 'gloo' backend (Windows doesn't support 'nccl'), we may need to modify the following deepspeed src file before running 'build_win.bat' for...

@erew123 I tried another deepspeed wheel available in the internet (https://www.linkedin.com/pulse/deepspeed-wheels-windows-furkan-g%C3%B6z%C3%BCkara-vb7vf/?trk=article-ssr-frontend-pulse_more-articles_related-content-card). It is deepspeed 0.11.2 with py310 and it gave the same error for gloo distributed backend. I'll try on...

Hope to see the training code with training dataset (want to compare dreamoving with DISCO).