Object Detection application right in your browser. Serving YOLOv8 in browser using tensorflow.js
with webgl
backend.
Setup
git clone https://github.com/Hyuto/yolov8-tfjs.git
cd yolov8-tfjs
yarn install #Install dependencies
Scripts
yarn start # Start dev server
yarn build # Build for productions
YOLOv8n model converted to tensorflow.js.
used model : yolov8n
size : 13 Mb
Use another model
Use another YOLOv8 model.
Export YOLOv8 model to tfjs format. Read more on the official documentation
from ultralytics import YOLO
# Load a model
model = YOLO("yolov8n.pt") # load an official model
# Export the model
model.export(format="tfjs")
Copy yolov8*_web_model
to ./public
Update modelName
in App.jsx
to new model name
...
// model configs
const modelName = "yolov8*"; // change to new model name
...
Done! 😊
Note: Custom Trained YOLOv8 Models
Please update src/utils/labels.json
with your new classes.