search

deshwalmahesh / yolov7-deepsort-tracking

Modular and ready to deploy code to detect and track videos using YOLO-v7 and DeepSORT
158 stars 65 forks source link

dead kernel is showing while running the code...please help #21

Open koustav051199 opened 1 year ago

deshwalmahesh commented 1 year ago

Can you explain a bit on the problem?

aarushi-sahu commented 1 year ago

@deshwalmahesh Hello, I am also facing the same issue with the code while running the Jupyter notebook script (Object tracking part). Also, bounding boxes were generated earlier but now it is showing an input image in the output. Please help me out, anyone. Screenshot (1481)

deshwalmahesh commented 1 year ago

@deshwalmahesh Hello, I am also facing the same issue with the code while running the Jupyter notebook script (Object tracking part). Also, bounding boxes were generated earlier but now it is showing an input image in the output. Please help me out, anyone. Screenshot (1481)

@aarushi-sahu Which model are you using? It happens if you have less RAM than the overall process needs. You can try clearing up extra things from memory, use a batch size of 1, using smaller image input size, smaller model sizes etc.

It might also be due to the fact that you're trying to manipulate a video of some significant time + HD + High FPS which might blow out of proportion.

aarushi-sahu commented 1 year ago

I am using the same model as you (yolo v7 with deep sort tracking) on a 16 GB RAM computer with a windows operating system. I also tried it with a smaller batch size, but it didn't work. I am not getting what exactly is going wrong. Please help me with this.

deshwalmahesh commented 1 year ago

I am using the same model as you (yolo v7 with deep sort tracking) on a 16 GB RAM computer with a windows operating system. I also tried it with a smaller batch size, but it didn't work. I am not getting what exactly is going wrong. Please help me with this.

@aarushi-sahu Are you able to use the Colab version? I think your Video is too Big to be handled. Try using a smaller video of smaller size on Colab.

aibatchelor22 commented 10 months ago

I am having the same issue, 16 GB of RAM. I am using yolov7.pt weights and the demo video from the repo. The video is only 3.5 MB, so I doubt the video itself is overloading the RAM.

aibatchelor22 commented 10 months ago

I figured out the problem. Changing the argument show_live = True to show_live = False fixed it.