Brian
This issue is still unsolved seems the program stuck at waiter.acquire() which is in lib/python3.7/threading.py", line 296, in wait
I know it have to normalize the weight but why do we need this line: x = F.normalize(x, p=2, dim=1) why normalize feature?
Anyone can kindly provide the voxceleb1 & voxceleb2 datasets? It takes a huge amount of time to download & crop the video in this repo: https://github.com/AliaksandrSiarohin/video-preprocessing , and most of...
Hi, could you provide the latest download script? It seems that the link is broken now. Thank you
Hi, I'm wondering how much memory is required? I've lower the batch_size to 1 and even decrease the embedding_layer but still OOM with my RTX3080 (10G)
/home/brianw0924/anaconda3/envs/GaitGraph2/lib/python3.10/site-packages/pytorch_lightning/utilities/cli.py:896: UserWarning: Failed parsing docstring for : docstring-parser package is required rank_zero_warn(f"Failed parsing docstring for {component}: docstring-parser package is required") /home/brianw0924/anaconda3/envs/GaitGraph2/lib/python3.10/site-packages/pytorch_lightning/utilities/cli.py:896: UserWarning: Failed parsing docstring for : docstring-parser package is...
The official website removed the dataset link could you provide the vox dataset?
Can anyone share the approximate time to run all voxceleb dataset? (with GPU info provided)
just wondering what is the parameter in get_mean_style means... and the function style_mixing, what does n_target, n_source mean?