Flowerfan

Thank you for the re-testining. Could you provide me with the txt_msrvtt.json file that contains the 1k test videos? There are only 50 videos in https://github.com/tsujuifu/pytorch_violet/blob/main/_data/txt_msrvtt-retrieval.json

I just tested with my txt file, and got 'r@1': 0.233, 'r@5': 0.533 with the ckpt_violet_pretrain.pt. This is my generated [txt file](https://drive.google.com/file/d/1aHC-vnPch5BizfmSuE6CLE-IAVPOSIR4/view?usp=sharing).

I just tested your file with the ckpt_violet_pretrain.pt using your repo, but still got r@1': 0.233, 'r@5': 0.533 :joy: . Have no idea what's wrong

Hi, Just wondering how you process the Youcook2 dataset for evaluation since one video contains multiple clip-text pairs. I have extracted clip-text pairs (3400) for evaluation and got a very...

1. The model trained with human single frame annotations in Table 1 is the model in the last low of Table 3. You can get the model by running ``python...

My account to access Google Drive was removed after graduation. Checkpoints with a little higher performance after training with the dist_train.sh on the combined datasets.

you need to compile the repo first while install the setup.py