BLIP/configs/retrieval_msrvtt.yaml

video_root: '/export/share/dongxuli/data/msrvtt_retrieval/videos'
ann_root: 'annotation'

# set pretrained as a file path or an url
pretrained: 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_retrieval_coco.pth'

# size of vit model; base or large
vit: 'base'
batch_size: 64
k_test: 128
image_size: 384
num_frm_test: 8