The number of the frames of the video dataset seems to be wrong
Like the 111.mp4,it has 1050 frames,but has 1203 GT saliency maps in your dataset.
Hello, i am facing the same problem. Also there are less saliency maps than extracted frames in many videos. Did you find any solution? Thanks in advance
我也遇到啦同样的问题,通过cv2.VideoCapture生成的视频帧数和gt数量不一致;
finally I came to the conclusion that the problem is that some GTs are missing in several of the videos. try different libraries to extract the frames. Then the problem is that you may have higher number of frames than GTs. From my research, I concluded that the last GTs are missing. So you delete the last frames that are not connected with any GT.