visual-layer / fastdup

fastdup is a powerful free tool designed to rapidly extract valuable insights from your image & video datasets. Assisting you to increase your dataset images & labels quality and reduce your data operations costs at an unparalleled scale.
Other
1.56k stars 76 forks source link

YOLOv5 Object Detection Notebook #142

Closed dnth closed 1 year ago

dnth commented 1 year ago

This PR adds an initial working version of using YOLOv5 with fastdup using the V1 API.

Try out the notebook here https://colab.research.google.com/github/dnth/fastdup/blob/dnth/video-yolo-detection/examples/video-yolov5-detection.ipynb

Feedbacks welcome.