Name: sidedish
Type: User
Company: Intellifusion Tech Co., Shenzhen, China
Bio: System Software Engineer, experienced C/C++ developer, familiar with Linux Kernel、Kernel-based Virtual Mahchine and Deep Learning Compilation/Quantization
Location: Shenzhen&&Chengdu
sidedish's Projects
This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors (HSW+) and Intel® Xeon Phi processors
Convolutional Neural Networks
RFC for common in-memory tensor structure and operator interface for deep learning system
Loongson CQ DOCs
Open deep learning compiler stack for cpu, gpu and specialized accelerators
libjpeg-turbo-1.3.0 with loongson simd optimation
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch and CoreML.
MXNet port of SSD: Single Shot MultiBox Object Detector. Reimplementation of https://github.com/weiliu89/caffe/tree/ssd
Bring deep learning to bare metal
Open Neural Network Exchange
Tensorflow Backend and Frontend for ONNX
Enable and optimize loongson mmi in pixman(about 0.29).
QuestionAnsweringSystem是一个Java实现的人机问答系统,能够自动分析问题并给出候选答案。
recommend system study
Meta info for Sophon TVM
OpenCL support for TensorFlow