Bolt is a deep learning library with high performance and heterogeneous flexibility.

The repository is the code for the paper "End-to-End Video Object Detection with Spatial-TemporalTransformers"

A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.

Reducing spatial redundancy in video recognition. SOTA computational efficiency.

LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)

Action Graphs: Weakly-supervised Action Localization with Graph Convolution Networks

Pytorch implementation of FlowNet by Dosovitskiy et al.

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）