Views
No views yet
python -m torch.distributed.launch --nproc_per_node=1 --use_env train_vlp_v2.py --batch-size 4 --epochs 80 --opt sgd --lr 0.01 --output_dir out/vlp_v2 --training-refurbish True --noise-rate 0.15 --noise-type omit_last --random-shuffle False --input-size=128 --num_workers=21python -m torch.distributed.launch --nproc_per_node=1 --use_env train_slt.py --batch-size 2 --epochs 200 --num_workers=2 --input-size=128 --opt sgd --lr 0.01 --output_dir out/ASL-Gloss-Free \
2--finetune ./out/vlp_v2/checkpoint.pthpython -m torch.distributed.launch --nproc_per_node=1 --use_env train_slt.py --batch-size 2 --epochs 200 --opt sgd --lr 0.01 --output_dir out/ASL-Gloss-Free-2 --resume out/ASL-Gloss-Free-2/best_checkpoint.pth --eval --num_workers=21@InProceedings{Zhou_2023_ICCV,
2 author = {Zhou, Benjia and Chen, Zhigang and Clap\'es, Albert and Wan, Jun and Liang, Yanyan and Escalera, Sergio and Lei, Zhen and Zhang, Du},
3 title = {Gloss-Free Sign Language Translation: Improving from Visual-Language Pretraining},
4 booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
5 month = {October},
6 year = {2023},
7 pages = {20871-20881}
8}