search

showlab / all-in-one

[CVPR2023] All in One: Exploring Unified Video-Language Pre-training
https://arxiv.org/abs/2203.07303
277 stars 16 forks source link

How to test the model? #3

Closed Daniel-Kelvich closed 2 years ago

Daniel-Kelvich commented 2 years ago

Hi! I want to test video retrieval with all-in-one-base.ckpt on MSR-VTT and see the metrics to compare with the paper. Can you please help with the command? I tried the following command but it started to train the model and I only need testing. python run.py with data_root=data/ num_gpus=2 num_nodes=1 per_gpu_batchsize=32 task_finetune_only_ind_itc_msrvtt_randaug num_frames=3 load_path="pretrained/all-in-one-base.ckpt"

FingerRec commented 2 years ago

Hi Daniel: Our work focus on general pre-training and the provided weight is pre-trained weight.

You need to fine tune this model for downstream fast retrieval, look at Section Downstream Tasks-Text-video Retrieval for details.

BTW, be careful. :)

pribadihcr commented 8 months ago

Hi Daniel: Our work focus on general pre-training and the provided weight is pre-trained weight.

You need to fine tune this model for downstream fast retrieval, look at Section Downstream Tasks-Text-video Retrieval for details.

BTW, be careful. :)

where is the section README?