hateful_memes-hate_detectron

hateful_memes-hate_detectron copied to clipboard

why we could use mmf_run to run the project?

3

why we could use mmf_run to run the project? what is th main function of the project?

fengmingfeng

!mmf_run config="projects/visual_bert/configs/hateful_memes/from_coco.yaml" \ model="visual_bert" \ dataset=hateful_memes \ run_type=train_val \ checkpoint.max_to_keep=1 \ checkpoint.resume_zoo=visual_bert.pretrained.cc.small_fifty_pc \ training.tensorboard=True \ training.checkpoint_interval=50 \ training.evaluation_interval=50 \ training.max_updates=3000 \ training.log_interval=100 \ dataset_config.hateful_memes.max_features=120 \ dataset_config.hateful_memes.annotations.train[0]=$train_dir \ dataset_config.hateful_memes.annotations.val[0]=$dev_unseen \ dataset_config.hateful_memes.annotations.test[0]=$test_unseen...

fengmingfeng

I am getting an error when trying to finetune VisualBERT pretrained model on Hateful Meme Dataset. Not sure why it is looking for dev.jsonl when there is no such jsonl...

AnjumJ123

ValueError: value should be one of int, float, str, bool, or torch.Tensor

1

shiyill

Hi, can you please help me in how i can use my dataset as input to your model. my dataset consist of a folder where all the image is stored...

kajukismis

ERROR: Could not build wheels for pycocotools, tokenizers, which is required to install pyproject.toml-based projects

Arnavsmayan