University science project aims to identify weeds from crops during their early seedling phase. (WIP) This repository contains the source code and the instructions to build a object detection model that takes in pictures/videos of both weeds and crops together. Our goal is to figure out a method which can safely remove the detected weeds with minimun harm to the crops. <3
1. Prepare custom dataset.
2. Train YOLO/Tensorflow Object Detection Model.
3. Convert model to TFLite.
4. Run inference (image/webcam/microcontroller).
References:
- Tensorflow 2 Object Detection API tutorial: https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/index.html
- Nicholas Renotte: https://youtu.be/yqkISICHH-U?si=J4U9HKz3bjdDB1xQ