Using an ONNX Resnet model in Java
Hello everyone! 👋
This is a follow-up post to the previous one. Long story short, I started taking the course from fast.ai to learn more about Deep Learning. I’ve built a simple Image Tagging model using the Resnet architecture (don’t worry about the paper I did not read it, GitHub Copilot suggested it while writing this blog post).
FastAI is a high-level Python library that allows you to train complex ML models really fast and efficiently. After training my model, I’ve exported it into the ONNX format and in this post, we’re using the model in a Java application.
The model will do image keywording. You can give it an image, and it will give you some keywords that describe the image. If you’re a photographer, you can use this model to tag your images and make them easier to find. 📸