Alternatives and similar repositories for caffe

Users that are interested in caffe are comparing it to the libraries listed below

• jonathantompson / jtorch
  An OpenCL Torch Utility Library
  ☆59Updated 9 years ago
• seung-lab / znn-release
  Multi-core CPU implementation of deep learning for 2D and 3D sliding window convolutional networks (ConvNets).
  ☆94Updated 9 years ago
• moskewcz / boda
  Boda: A C++ Framework for Efficient Experiments in Computer Vision
  ☆64Updated 6 years ago
• hughperkins / clnn
  OpenCL backend for Torch nn neural networks library
  ☆126Updated 9 years ago
• naibaf7 / libdnn
  Greentea LibDNN - a universal convolution implementation supporting CUDA and OpenCL
  ☆137Updated 8 years ago
• eBay / maxDNN
  High Efficiency Convolution Kernel for Maxwell GPU Architecture
  ☆137Updated 8 years ago
• szagoruyko / nnpack.torch
  Torch FFI-bindings for NNPACK
  ☆31Updated 8 years ago
• naibaf7 / caffe
  Caffe: a fast open framework for deep learning. With OpenCL and CUDA support.
  ☆87Updated 7 years ago
• NervanaSystems / cuda-convnet2
  Custom fork containing our own python backend for integration into neon
  ☆15Updated 3 years ago
• hughperkins / cltorch
  An OpenCL backend for torch.
  ☆301Updated 9 years ago
• facebookarchive / thpp
  TH++, C++ interface to the torch7 TH library
  ☆246Updated 7 years ago
• opveclib / opveclib
  The Operator Vectorization Library, or OVL, is a python productivity library for defining high performance custom operators for the Tenso…
  ☆68Updated 9 years ago
• MatthieuCourbariaux / deep-learning-multipliers
  Training deep neural networks with low precision multiplications
  ☆64Updated 10 years ago
• hctomkins / caffe-gui-tool
  Node based Gui for creating caffe networks
  ☆103Updated 5 years ago
• deeplearningais / CUV
  Matrix library for CUDA in C++ and Python
  ☆196Updated 9 years ago
• uoguelph-mlrg / Theano-MPI
  MPI Parallel framework for training deep learning models built in Theano
  ☆54Updated 8 years ago
• milakov / nnForge
  Convolutional neural networks C++ framework with CPU and GPU (CUDA) backends
  ☆182Updated 7 years ago
• torch / cunn
  ☆214Updated 6 years ago
• hantek / BinaryConnect
  Source code for ``Neural Networks with Few Multiplications'' published at ICLR 2016
  ☆80Updated 9 years ago
• Alexey-Kamenev / Benchmarks
  Benchmarks for CNTK and other toolkits.
  ☆44Updated 10 years ago
• NervanaSystems / ngraph-python
  Original Python version of Intel® Nervana™ Graph
  ☆214Updated 3 years ago
• codekansas / tinier-nn
  Binarized Neural Network TF training code + C matrix / eval library.
  ☆101Updated 8 years ago
• attractivechaos / matmul
  Benchmarking matrix multiplication implementations
  ☆103Updated 9 years ago
• hannes-brt / cudnn-python-wrappers
  Python wrappers for the NVIDIA cuDNN libraries
  ☆142Updated 8 years ago
• NVIDIA / pynvrtc
  Python Binding to NVRTC
  ☆79Updated last year
• benanne / theano_fftconv
  Convolution op for Theano based on CuFFT using scikits.cuda
  ☆51Updated 11 years ago
• TorontoDeepLearning / convnet
  A GPU implementation of Convolutional Neural Nets in C++
  ☆505Updated 5 years ago
• openai / openai-gemm
  Open single and half precision gemm implementations
  ☆398Updated 2 years ago
• jhjin / flattened-cnn
  Flattened convolutional neural networks (1D convolution modules for Torch nn)
  ☆61Updated 10 years ago
• facebookarchive / fbcuda
  Facebook's CUDA extensions.
  ☆284Updated 6 years ago