Latest Release

Jan 24, 2018   |  

neon™ 2.6.0: Inference Optimizations for Single Shot MultiBox Detector on Intel® Xeon® Processor Architectures

We are excited to release the neon™ 2.6.0 framework, which features improvements for CPU inference path on a VGG-16 based Single Shot multibox Detector (SSD) neural network. These updates, along with the training optimizations released in neon 2.5.0, show that neon is gaining significant boosts in both training and inference performance.  (Granular configuration details, as well…

Read more

#neon #Release Notes

Model Zoo

neon™ comes with its own Model Zoo featuring pre-trained weights and example scripts for state-of-the-art models — the ones you see below are just a few.

Visit the Repository

Image Classification

- GoogLeNet
- Alexnet

- Deep Residual Network
- All CNN

Learn more

Object Localization


Learn more

Scene Classification

Deep Residual Network

Learn more

Image Captioning


Learn more

Video Games

Deep Q-network

Learn more


bAbI (Question Answering)
-GRU/LSTM model
sentiment classification
-LSTM (IMDB dataset)

Learn more


C3D (UCF101 dataset)

Learn more


Deep Speech 2 (Librispeech dataset)

Learn more


Video Recognition

A fast 3D convolution network, C3D-based model for activity recognition using neon on the UCF-101 dataset.

Automatic Speech Recognition

Neon’s implementation of Baidu’s "Deep Speech 2" model for speech recognition trained on audio-books from the Librispeech corpus.
Spectrogram (top left), raw audio (top right), and FFT spectrum (bottom).

Sentiment Analysis

A LSTM-based model constructed in neon to perform sentiment analysis on live Twitter* stream.

Demo Playlist

Stay Connected

Keep tabs on all the latest news with our monthly newsletter.