Yangqing Jia's Projects
CMake toolchain file and other scripts for the Android NDK
A packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface
C/C++ beanstalk client
A microbenchmark support library
Barnes-Hut t-SNE
Caffe: a Fast framework for neural networks. For the most recent version, check out branch dev. For a more stable version, check out branch master.
This is currently an experimental refactoring of Caffe.
Easy benchmarking of all public open-source implementations of convnets
This is my original repository of the decaf code. Decaf is a precursor of Caffe written in Python for deep image classification. It is deprecated, and you should check out my new library, Caffe, at http://caffe.berkeleyvision.org/.
Demo of running NNs across different frameworks
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
For Ed. Just quick code to try dllexport settings.
RFC for common tensor and operator guideline in deep learning system
Dense sift (Dsift) feature extraction using python and numpy.
A library for efficient similarity search and clustering of dense vectors.
The FastPFOR C++ library: Fast integer compression
Conversion to/from half-precision floating point formats
Header-only library for division via fixed-point multiplication by inverse
A set of collective operations that provides primitives for multi-machine training of machine learning models.
a language for image processing and computational photography
some experimental code
A toolchain file and examples using cmake for iOS development (this is a fork of a similar project found on code.google.com)
A Pythonic framework to simplify AI service building
Fast exact nearest neighbor search in Hamming distance on binary codes with Multi-index hashing
Lightweight MapReduce in python
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
Optimized primitives for collective multi-GPU communication