New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
joint training hyper parameters #7
Comments
BTW, would you like to share your script for pretraining, thanks! |
Hi, We use 32 V100 GPUs with 32G memory. And sorry for the mistake, it is actually is 1 for joint training and 2 for pretraining. We do not support multi-node training in the repo now. For single node training, the pretraining script is python3 -m torch.distributed.launch --nproc_per_node=8 --use_env \
main_pretrain.py --dataset_file all --binary --with_box_refine \
--batch_size 2 --num_frames 1 \
--epochs 12 --lr_drop 8 10 \
[backbone] |
Thank you for your information! |
Did you freeze text encoder during pretraining? |
The text encoder is not frozen for pretraining. While for joint training, it is frozen. |
I think I found the reason I cannot reproduce the result...The paper has some ambiguity for this part. Thank you. |
Hi, May I ask why you freeze the text encoder during joint training? Since the joint training doesn't need a pretraining process, I would assume the text encoder is not trained? Thank you! |
We have experimented whether to freeze the text encoder with the R50 backbone. And we found freezing the text encoder would have 1+ points gain. |
Thank you very much! |
Hi,
Thank you for sharing your work. I am writing to inquire the hyper parameters used for joint training. The arxiv paper mentioned that
which says that the joint training uses 32 V100 GPUs and 2 video clips for each GPU.
I consider it means 32G V100 GPU. But I think it's not possible to add 2 video clip within 32G memory. I cannot reproduce the result using 8 V100 32G GPU with 1 clip per GPU, would you like to give me some advice? Thank you!
The text was updated successfully, but these errors were encountered: