Codes of Interest is proud to present Bird Watch, a Deep Learning Computer Vision tool to identify bird species from images. It was built for wildlife photographers, bird and nature lovers, researchers, and academics alike.
Bird Watch is now in v0.3.0 Beta and is available for anyone to use free of charge at,
 |
| Bird Watch in action |
The system was built using transfer learning, with the InceptionV3 model. It uses Keras, TensorFlow, and OpenCV for its underlying features. The web frontend is built using Flask.
It was trained with a data set of nearly 15000 (and growing) images and was trained and fine-tuned for over a hundred hours.
The current model looks like this,
 |
| The current model of Bird Watch (view larger at https://www.birdwatch.photo/howitworks) |
Still being a beta, it has some limitations. It can currently only identify 233 species of birds. misclassification is a possibility. But we're regularly adding more categories and tuning the model for better accuracy. Check here to see what bird species are supported as of now.
This is an Opensource project. You can find our GitHub repository with the full code and the model weights here: https://github.com/Thimira/bird_watch
This is an Opensource project. You can find our GitHub repository with the full code and the model weights here: https://github.com/Thimira/bird_watch
Stay tuned for more updates...
Learn the bleeding edge of AI in the most practical way: By getting hands-on with Python, TensorFlow, Keras, and OpenCV. Go a little deeper...
Get your copy now!
No comments:
Post a Comment