Search subjects/objects in an image using simple text description and get cropped results.
Try it on Colab:
-side.png)
-side.png)
-side.png)
- This is done by combining Object detection yolov5 and OpenAI's CLIP model.
- Detects and crops objects (yolov5s)
- Encode cropped images using CLIP
- Encode search query using CLIP
- Find the best match
- #vacation
☺️
Can also be used to create datasets with some changes in code. In the below example images of Jack daniels bottle has been croped and saved.
- Depends heavily on object detection(yolov5).
- YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, So detection depends on COCO classes.