wnzhyee

which transformers version and pytorch version should be installed?

2

I try to use layoutlmv2model, and install the unilm following the layoutlmft: ``` datasets==1.6.2 torch==1.7.1+cu101 torchvision==0.8.2+cu101 transformers==4.5.1 detectron2==0.3 seqeval==1.2.2 ``` this install successed but it reports **"LayoutLMv2Model" is not in...

https://github.com/facebookresearch/jepa/blob/69f2ae1519c8844581c8a1f3db0f34f4287a6011/evals/video_classification_frozen/eval.py#L98 this line should be eval_frame_step = **args_data**.get('frame_step', 4) cause of args_pretrain does not have frame_step param in config.yaml

Hi, I just notice the csv split files which author provided in [google_drive](https://drive.google.com/drive/folders/1cfA-SrPhDB9B8ZckPvnh8D5ysCjD-S_I), the **test.csv** and **val.csv** is same, total 24777 samples. This split should be ssv2 offical validation split,...