conceptual caption dataset, you can download the precomputed features through link (the files are being uploaded)

then unzip your downloaded file, obtain the fold cc, and move it to the fold ./dataset

MS coco dataset, you can download the precomputed features through this link

Alternatively, you can obtain it in command line by

wget https://www.dropbox.com/s/4g0x49h302xj7j4/coco.tar.gz?dl=0

then unzip your downloaded file, obtain the fold coco, and move it to the fold ./dataset

you can download the pretrained bert model through this link

then move your downloaded .bin file to ./bert fold

you can download the pretrained bert model through this link

then move your downloaded .bin file to ./models fold

python train.py --task pretrain --mlm --cm

python train.py --task retrieval --resume models/6layer_mlm_pretrain.pth.tar