Yair Schiff
Yair Schiff
@monk1337 thank you for the interest in the code. I think you can use the TabFormer BERT model to embed your data and then run an unsupervised clustering algorithm in...
@sentialx , agreed. That's a good catch.
> how the speed compares to uni-directional? @jimmieliu, it's about 2x
@phizaz, just wanted to check in on this again. Are you planning to release code for reproducing [Table 8](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Preechakul_Diffusion_Autoencoders_Toward_CVPR_2022_supplemental.pdf) by any chance? Thanks!
Thanks for taking a look!
Wanted to check this issue as well. My existing workflow of `trainer.fit(..., ckpt_path=)` is also currently blocked because of the default behavior change in torch 2.6
@ORippler , I see, thanks. I think it's actually `2.2` that I'm using. I'll try upgrading
Any update on this? `torch 2.6` changed default behavior to have `weights_only=True` which is breaking my workflow of `trainer.fit(ckpt_path=ckpt_path)`
@katosad, a bit hacky, but I think you can set `TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1` environment variable to avoid this breaking behavior for now. Hope that helps! (ref: [pytorch docs](https://docs.pytorch.org/docs/stable/miscellaneous_environment_variables.html))