search

facebookresearch / mmbt

Supervised Multimodal Bitransformers for Classifying Images and Text
Other
243 stars 52 forks source link

Run on GQA dataset #4

Closed yonatanbitton closed 3 years ago

yonatanbitton commented 3 years ago

Hello Do you have an instructions to run MMBT on the GQA dataset? I've tried to make changes in the repo but it doesn't seem to work.

I've tried to run with this CMD: python mmbt/train.py --batch_sz 4 --gradient_accumulation_steps 40 --savedir /users/yonatan/mmbt/savedir --name mmbt_model_run --data_path /users/yonatan/gqa_data_and_images_dir --task food101 --task_type classification --model mmbt --num_image_embeds 3 --freeze_txt 5 --freeze_img 3 --patience 5 --dropout 0.1 --lr 5e-05 --warmup 0.1 --max_epochs 100 --seed 1 Thank you

douwekiela commented 3 years ago

Hi, sorry I somehow missed this. I don't think the --task food101 argument is appropriate for GQA, unless you converted it to the food101 format?