-
I want to use this code base to test the performancc ALPRO on MSRVTTT, but I did not find the tutorial of how to process video and do a text to video retrieval.
-
Hi,
I want to train the model using the MSR-VTT dataset. And it tells me that I need a pkl file but I can only find the mp4 and txt files. So how can I tranfer them to or maybe to find the pkl file.
-
Hi, thank you for sharing the model.
For the evaluation the line suggest to use 6144 for the embedding:
python eval.py --eval_msrvtt=1 --eval_youcook=1 --eval_lsmdc=1 --num_thread_reader=8 --embd_di…
-
Hello, thanks for your awesome work!@kevinlin311tw
I have noticed that in your official tutorial of multi-gpus training, when facing with 2 gpus, you set args.learning_rate = 3*e-4 and args.backbon…
-
Thanks for sharing your code. Is it normal to get R1=30 with train_titles.py? After running the score fusion, the title matrix does not improve the video matrix.
-
Hi! I'm trying to pretrain VindLU using 5M data, can you provide the pretraining logs for reference? Thanks!
-
Hi,
I was trying to download the pre-extracted features through the link https://bit.ly/2TX9rlZ. But accessing the link gives me the error "We're sorry, but qh53@cornell.edu can't be found in the …
-
-
Hello. Thank you for sharing your interesting research.
I was able to easily reproduce the results of the DiDeMo dataset by demo script (run_didemo.sh). However, when attempting to reproduce the MSR-…
-
Can you share some recordings of your experiments like some graphs in neptune.ai or other logs tracking the performance/loss changes in training steps.
I would like to compare the effects of some c…