Libra: Ergonomic machine learning
The recent emergence of machine learning has given rise to hundreds of different frameworks, so why would you use Libra? Here’s why libra outperforms all these other alternatives.
Libra prioritizes ease of use and ergonomics.
- Libra is a machine learning API designed for non-technical users. This means that it assumes that you have no background in ML whatsoever.
- Never preprocessed data before? Never worked with complex graphing libraries to analyze your models? Never understood what a dropout or a pooling layer does? Perfect. None of this knowledge is required to get your hands dirty in machine learning with Libra.
- This makes it very easy to test the possibility of machine learning in your work enviroment. Don’t go out and hire a machine learning engineer before you know it’s possible to integrate the technology in your current system. Be confident first.
- This ease of use does not come at the cost of reduced flexibility: all parameters that can be passed into Scikit-Learn and Keras algorithms can also be passed to Libra. On top of this, we’ve already setup preprocessing pipelines for you to tune if you’d like!
We’ve combined technologies from the most popular platforms to create a complete experience
- Keras: straightforward model building techniques for improved modularity and ease of deployment.
- TensorFlow: core computational fundamentals and detailed functionality.
- PyTorch: scalable training for highly-dimensional processes.
- Scikit-Learn: one-line quick model building capabilities.
- Keras-Tuner: class-wise structure for intelligent neural network-tuning.
Libra home page is https://libradocs.github.io/index.html