YM

In addition, according to the [official document](https://github.com/facebookresearch/detectron2/releases), looks like detectron2==0.1 is incompatible with torch==0.6? The former is installed by `cd vilio/py-bottom-up-attention; python setup.py build develop` via cloned detectron2 source, while...

Also, for detectron2 import error I needed to copy `detectron2_mscoco_proposal_maxnms.py` to different location and change the argument of `hm_feats.bash` pointing that python script to new path. Refer to aforementioned official...

`FastRCNNOutputs` was removed in detectron2 0.6. In my case downgraded to [0.5](https://github.com/facebookresearch/detectron2/issues/3715). Also, `transform_gen` should be replaced with `aug` to use with 0.5/0.6 ([reference](https://github.com/facebookresearch/detectron2/issues/2247))

@ronghanghu Thanks for your comment. Now the error turned to this ``` Traceback (most recent call last): File "/home//anaconda3/envs/mmf/bin/mmf_run", line 33, in sys.exit(load_entry_point('mmf', 'console_scripts', 'mmf_run')()) File "/home///mmf_cli/run.py", line 133, in...

Hi, met the same issue when trying below; ``` from mmf.models.vilbert import ViLBERT model = ViLBERT.from_pretrained("vilbert.finetuned.hateful_memes.direct") ``` In my case I did the manual fixes as below to `~/.cache/torch/mmf/data/models/vilbert.finetuned.hateful_memes.direct/config.yaml`; ```...

Met the same error, in my case when trying to reproduce [UniT tutorial](https://mmf.sh/docs/projects/unit/). @BrandonHanx 's solution worked for me, and then `no module named future` popped up, and then [this...

Not yet, but could #432 give us the basic idea? According to [finetune-by-yourself doc](https://github.com/haotian-liu/LasLaVA/blob/5d8f1760c08b7dfba3ae97b71cbd4c6f17d12dbd/docs/Finetune_Custom_Data.md#L4), we should use [train.py](https://github.com/haotian-liu/LLaVA/blob/main/llava/train/train.py) for this purpose. In case of evaluation, I needed to 1) load...

Decided to use module-friendly environment

Seeing this page, looks like the testing code throwed an error and the package was left unupdated. https://cran-archive.r-project.org/web/checks/2019/2019-12-21_check_results_mvtboost.html

Interested in multiple image input as well. We're wondering if we could perform multimodal few-shot classification (on-the-fly, without fine-tuning) or not. Will test Vishaal's solution and maybe create PR when...