International Birds Classification

Challenge

The Imagenet Challenge only have 1000 different categories. How about using deep learning technology to classify 11000 different types of birds in the world ?

Implementation

In this project, I will try to use Single Shot MultiBox Detection to detect birds in a general picture, and also use EfficientNet to classify them.

What I learned

I learned how to use PyTorch to load image datasets, build models. From this project, I also intensively read the detailed implementation of Single Shot MultiBox Detection.

Built With

• deeplearning
• flask
• python
• pytorch