pooya-mohammadi/yolov5-gradcam
Visualizing Yolov5's layers using GradCam
This tool helps researchers and AI practitioners understand why a YOLOv5 object detection model identifies specific objects in an image. You provide an image and a trained YOLOv5 model, and it generates visual heatmaps highlighting the exact regions of the object the model focused on. This helps debug model behavior and gain insights into its decision-making process.
296 stars. No commits in the last 6 months.
Use this if you need to visualize which parts of an image your YOLOv5 model pays attention to when detecting objects, to validate or debug its performance.
Not ideal if you are using an object detection model other than YOLOv5, or if you only need the detection results without explanation.
Stars
296
Forks
47
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/pooya-mohammadi/yolov5-gradcam"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.