neonΒΆ

Release:1.0.0+cef40c9
Date:October 30, 2015

neon is Nervana‘s Python-based deep learning library. It provides ease of use while delivering the highest performance.

Features include:

  • Support for commonly used models including convnets, RNNs, LSTMs, and autoencoders
  • Tight integration with our state-of-the-art GPU kernel library
  • 3s/macrobatch (3072 images) on AlexNet on Titan X (Full run on 1 GPU ~ 32 hrs)
  • Swappable hardware backends: write code once and deploy on CPUs, GPUs, or Nervana hardware

New features in this release:

  • Fast image captioning model (matches CPU based NeuralTalk while ~200x faster)
  • Basic automatic differentiation support
  • A framework for visualization
  • and many more.

We use neon internally at Nervana to solve our customers’ problems in many domains. Consider joining us. We are hiring across several roles. Apply here!