neon™

Latest Release

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.

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.

Image Classification

ImageNet
GoogLeNet
VGG
Alexnet

CIFAR-10
Deep Residual Network
All CNN

GitHub

Object Localization

Fast-RCNN

GitHub

Scene Classification

Deep Residual Network

GitHub

Image Captioning

LSTM

GitHub

Video Games

Deep Q-network

GitHub

NLP

bAbI (Question Answering)
GRU/LSTM model

sentiment classification
LSTM (IMDB dataset)

GitHub

Video

C3D (UCF101 dataset)

GitHub

Speech

Deep Speech 2 (Librispeech dataset)

GitHub

neon Resources