Open ghost opened 11 months ago
same issue
If you use the NPS dataset, I know how to solve it. In the YAML which contains the labels and image paths, also have the video_root_path.
Put the train/val/test videos in each path and the code will count the number of frames in each video. The number of frames in each video seems to be used in the training process.
Hi! Thank you for your contribution. I encountered an error while running the train.py file. Do you know how to solve this problem?
The code I used is as follows. I'm looking forward to your reply!
![image](https://github.com/tusharsangam/TransVisDrone/assets/38455510/21d993f6-3890-400b-9860-3ee7a09c1ea1)