Open source Computer Vision toolkit

Star Fork

Out of the box usage

Open source and easy to use. Install it in your own servers and integrate it with your product right away.

Customizable object detection and classification models

Easily train neural networks to detect and classify objects with custom data. Use state of the art models such as Faster R-CNN.

Made with TensorFlow & Sonnet

Built on top of Google’s Deep Learning framework and DeepMind’s graph library.

Simple training

Train your model by just typing lumi train. Do it locally or using Luminoth's built-in Google Cloud Platform support to train in the cloud.

Once training is done, you can use our Tensorboard integration to visualize progress and intermediate results. Also, evaluate using different data splits.

Understand results

The ability to visualize results is always important and more so in the Computer Vision field. After training a model you can get an easy to understand summary and graph visualizations to spot results, using either our UI or the command line interface.

Try it now.

Want to know more? read our launch Blog post.