Maty Bohacek

Thanks for your interest in our work! For now, you can obtain training data in the supported format using Vision API (which was used in our original work, [WACV'22 paper](https://openaccess.thecvf.com/content/WACV2022W/HADCV/papers/Bohacek_Sign_Pose-Based_Transformer_for_Word-Level_Sign_Language_Recognition_WACVW_2022_paper.pdf))....

Thanks for opening this ticket, @Coco-hanqi. Yes, this seems strange, probably related to the under-performing accuracy. Let me try to reproduce this behavior on a new machine and investigate the...

Dear @Coco-hanqi & @caicairay, I finally managed to reproduce this on an older external machine. Upon further research, it seems that some PyTorch versions seem to have various low-level issues...

Thanks both — especially @RodGal-2020 for the explanation for others members in the thread during my absence. We will be providing more options of pose estimator formats like OpenPose, MMPose,...

Thank you for reporting! Could you please provide the full error trace? Thank you. (It is always ideal to have the CUDA_LAUNCH_BLOCKING=1 flag when running, so any low-CUDA errors shall...

Hello, thanks for your message. I will note to upload the training code along with the newly re-trained models soon. Will let you know in this thread.

Hi @adhithiyaa-git, It seems that wou are training the WLASL100 dataset (with 100 classes) but only using the default `--num_classes` argument, which is 64. This would cause the `IndexError`. Try...

Sorry, this is currently not included in this repo. Hope to add this in the near future!

+1

Hi there! Pose extraction is not included as part of this repo. I do plan to open-source those scripts eventually, but I’m not sure when I’ll get around to it....