Matej Grcić

Hi @alexm-gc, sorry for the late response. **A0.** DenseFlow-74-10 achieves BPD around 3.23 on the train set. I don't know the value of train BPD for VDM. Perhaps you should...

In my opinion, -log(n_bins) * n_pixel should be added per image, not per batch. Consequently, the loss should be calculated as follows: ``` def calc_loss(log_p, logdet, image_size, n_bins): n_pixel =...

Hi, thanks for pointing out the mismatch between the two versions of IN32. As far as I know, this is mostly unknown in the community and the old version being...