Brandon Victor
Brandon Victor
@joseph-pq I lost steam on this. Thanks for prompting. I tried merging this with master and it sucked. So I started from scratch with a different PR. Hopefully that one...
The default meaning of `epoch` in this codebase is "1250 iterations". See [here](https://github.com/facebookresearch/dinov2/blob/main/dinov2/train/train.py#L70) and [here](https://github.com/facebookresearch/dinov2/blob/main/dinov2/configs/ssl_default_config.yaml#L68) So, you just need to set your "epochs" and "warmup_epochs" appropriately for your batch size....
Just want to mention that I also have this problem. It seems that there is a conda conflict with `xformers=0.0.18` and `pytorch=2.0`. Full conda error ``` The following packages are...
It's a conflict between `xformers=0.0.18` and `pytorch=2.0`. I don't see how the CUDA version has anything to do with it. CUDA is [backwards compatible](https://docs.nvidia.com/deploy/cuda-compatibility/#use-the-right-compat-package), so having CUDA 12.x instead of...
It ran to completion. For my particular use case, the resulting model didn't work well, but I think that's more to do with my data than the code here. I...