Lists (8)
Stars
An Open Source Machine Learning Framework for Everyone
Protocol Buffers - Google's data interchange format
Productive, portable, and performant GPU programming in Python.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Seamless operability between C++11 and Python
a language for fast, portable data-parallel computation
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
CasADi is a symbolic framework for numeric optimization implementing automatic differentiation in forward and reverse modes on sparse matrix-valued computational graphs. It supports self-contained …
Vulkan/CUDA/HIP/OpenCL/Level Zero/Metal Fast Fourier Transform library
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
LibRaw is a library for reading RAW files from digital cameras
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
Code for our CVPR 2019 paper: Selective Kernel Networks; See zhihu：https://zhuanlan.zhihu.com/p/59690223
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
Open-L2O: A Comprehensive and Reproducible Benchmark for Learning to Optimize Algorithms
Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous em…
Direct solver for sparse SPD matrices for nonlinear optimization. Implements supernodal Cholesky decomposition algorithm, and supports GPU (CUDA).
An implementation of the paper Handheld Multi-Frame Super-Resolution
Designing image processing hardware and software for computer vision
Implementation codes of the decouple learning framework
Python bindings for scalar and vectorial models of the 3D microscope point spread function.