jackyjsy/sam-slr-v2

SAM-SLR-v2 is an improved version of SAM-SLR for sign language recognition.

sam-slr-v2's Issues

The uncorrect performance

Hello, I have trained the proposed model by myself and found the performance lower than reported in this paper on all datasets. And I found the performance is sensitive to the preprocessing and the hyper-parameters.

File name and directory structure for WLAS dataset preparation

Hi, I am interested in applying the SL-GCM algorithm to the WLASL dataset. I have not understood the steps to make and the folder structure in order to correctly use your code. First I downloaded the WLAS dataset following the instructions in https://github.com/dxli94/WLASL. Once processed with the preprocess.py python script I have all the videos in one folder named 'videos'. The name of each file is like univoque_id.mp4. At this point I should use the demo.py script in data-prepare/wholepose/ https://github.com/jackyjsy/data-prepare/tree/89b556b0cb49a5a401ed939e3977c101df912257/wholepose, but how should I rename the files? Should the sign made in the video appear in the name of the file? Moreover, Should I separate the files into a train, test and validation folder and apply the demo.py script to each separate folder?

Could you explain in more details the steps to be taken, how to structure the directory with the files, the files name and the commands to run?

Thanks

Normalization of 2D keypoints

Hello ,

In the paper it is mentioned that the 2D keypoints are normalized in [-1,1]
But when I print the keypoints after the feeder they do not look normalized at [-1,1].

Is this correct or I have done something wrong ?

Thank you in advance