Tensorrt model inference not working on folder of images and videos

[vardanagarwal]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

Detection

Bug

Running the default commands in the given colab notebook. Successful in creating a Tensorrt model but unable to run detect.py.

The same issue is faced on a folder of videos, however works on a single video.

Environment

No response

Minimal Reproducible Example

python3 detect.py --weights yolov5s.engine --imgsz 640 --device 0  # inference

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[glenn-jocher]

@vardanagarwal 👋 hi, thanks for letting us know about this possible problem with YOLOv5 🚀. I've run the code below and am able to reproduce the same issue you are seeing. I'll add a TODO and prioritize a fix for this.

# TensorRT 
!pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com  # install
!python export.py --weights yolov5s.pt --include engine --imgsz 640 --device 0  # export
!python detect.py --weights yolov5s.engine --imgsz 640 --device 0  # inference

[glenn-jocher]

@vardanagarwal good news 😃! Your original issue may now be fixed ✅ in PR #9581. I've also added exported model inference to our CI to catch this type of error earlier in the future.

To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!