Hongyang Gu

This method relies on the GMM to initialize the network, and you can get the final result by trying a few more times!

Yes. The core problem is still the algorithm itself. You can divide the training data into a part of the data as validation data, and use this data to find...

My setting is the same as the original paper. As you can see in the Decoder of model.py, the output is the parameters of the bernoulli distribution.

I've also noticed this issue, but my forward propagation is the same. After one iteration of backward propagation, inconsistencies appear. In addition, I've found that even when setting `num_workers >...

I found that setting a larger value for `num_workers` eliminates the issue of DataLoader worker (pid(s) 15804) exiting unexpectedly, which is similar to setting `num_workers` to 25 in https://github.com/hustvl/Vim/blob/main/vim/scripts/pt-vim-t.sh.