Danny (Zhiwei) Xu

> Hi @jfzhang95, > > When I trigger sync batchnorm, the training works fine, but the inference is quite weird. Loss in the inference is way too large. When you...

I did not think any one solved this problem, cuz 1.17 or 1.25 makes no sense. The released code and pretrained model on SceneFlow should have the results reported in...

I am having the same issue as above. I suggest the author(s) download this entire repository and re-download (_p2.pt) the pretrained models shown in the README link, and run the...

@leileqiTHU Hi, Have you figured out what the .jsonl file is in autoregressive/train/extract_codes_t2i.py? Thanks.

I agree, that means BARTScore is not intrinsically good at reasoning, even if the source context is given, the score for the target sentence sometimes has a discrepancy to the...