L2CS-Net
L2CS-Net copied to clipboard
Ahmednull
The official PyTorch implementation of L2CS-Net for gaze estimation and tracking
The preprocessing is not aligned with your training in your demo code. For the data preprocessing in training, the face images are first cropped to squares. It seems that u...
The command to run demo.py is 'python demo.py --snapshot models/L2CSNet_gaze360.pkl --device 0 --cam 0' It was. Also, the data_modified function does not exist in line 71 of the utils folder....
Is the pitch and yaw measured by your L2CS model in radians for gaze images? I tried to use your L2CS model to detect the gaze Angle of offline images,...
Implemented a fix for issue #22, where modern versions of numpy would ValueError when trying to process a frame without any detected faces. The fix simply defaults the return value...
Running into a numpy `ValueError: need at least one array to stack` when running the pipeline on a frame of video that has no faces detected. Seems to point back...
Hello, thank you very much for sharing such a great project. However, I seem to be encountering a problem where it is telling me that the "date_modified" module cannot be...
where is the output/snapshots/L2CS-gaze360-_loader-180-4/_epoch_55.pkl????
Hi. When you look at the inference predictions on provided [image](https://github.com/Ahmednull/Storage/blob/main/gaze.gif), when face/eye direction barely changes, inference predictions vary a lot sometimes. I was wondering if I can improve it...
Hi, thank you for your amazing work! I'm working on a mini program for gaze tracking in realtime based on l2cs. The realtime frame rate of this webcam demo is...
