Ahmed Taha

Hi LeoLiu2n, 1. In vanilla KE, the fit and reset hypotheses' binary-masks (Fig. 3) are fixed once initialized. Yet, it doesn't have to be like that. E.g., in the [Appendix-D:...

Hi LeoLiu2n I couldn't replicate your error. I tried the `resume` option myself and seems to work. My current guess is that you forget to **explicitly** provide other arguments. You...

The model_best.pth is the checkpoint that achieved the best performance on the validation set, while epoch_199.pth is the last checkpoint. I consistently use the last epoch. I know other people...

I am trying to replicate the results in this repos but my results lag as follows | 0.1 | 0.2 | 0.3 | 0.4 | 0.5 | 0.6 | 0.7...

I have been looking into this equation for sometime. I wrote my thoughts in the attached [main.pdf](https://github.com/openai/DALL-E/files/13805729/main.pdf). I believe we need to convert a single-variable distribution $q_{\phi}(z|x)$ into a multi-variable...