Alternatives and similar repositories for dnn

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

• OAID / MXNet-HRT
  Heterogeneous Run Time version of MXNet. Added heterogeneous capabilities to the MXNet, uses heterogeneous computing infrastructure frame…
  ☆72Updated 7 years ago
• dmlc / MXNet.cpp
  C++ interface for mxnet
  ☆115Updated 8 years ago
• MichalBusta / caffe
  Ristretto: Caffe-based approximation of convolutional neural networks.
  ☆30Updated 7 years ago
• xylcbd / blogs_code
  demo code of my blog
  ☆56Updated 2 years ago
• PerfXLab / embedded_ai
  ☆209Updated 7 years ago
• zhangxinqian / example-of-nnvm-in-cpp
  An Example of MXNet Models Comilation and Deployment with NNVM in C++
  ☆16Updated 7 years ago
• merrymercy / tvm-mali
  Optimizing Mobile Deep Learning on ARM GPU with TVM
  ☆181Updated 7 years ago
• HolmesShuan / Caffe-Computation-Graph-Optimization
  Caffe Computation Graph Optimization.
  ☆29Updated 5 years ago
• Yangqing / caffe2
  This is currently an experimental refactoring of Caffe.
  ☆96Updated 7 years ago
• zhreshold / mxnet-ssd.cpp
  C++ object detection module for mxnet-ssd
  ☆96Updated 8 years ago
• jhjin / tensorflow-cpp
  Image classification C++ example using tensorflow shared library
  ☆104Updated 8 years ago
• Maratyszcza / caffe-nnpack
  Caffe with NNPACK integration
  ☆59Updated 9 years ago
• strin / gemm-android
  tutorial to optimize GEMM performance on android
  ☆51Updated 9 years ago
• HongxingGao / XNOR-Net
  XNOR-Net, CUDNN5 supported version of XNOR-Net-caffe: https://github.com/loswensiana/BWN-XNOR-caffe
  ☆30Updated 7 years ago
• hyln9 / GCNGEMM
  Optimized half precision gemm assembly kernels (deprecated due to ROCm)
  ☆47Updated 8 years ago
• dongyp13 / Stochastic-Quantization
  Training Low-bits DNNs with Stochastic Quantization
  ☆74Updated 8 years ago
• aaalgo / xnn
  a C++ wrapper of Caffe and mxnet to make predictions
  ☆49Updated 7 years ago
• chinakook / MobileNetV2.mxnet
  A MXNet/Gluon implementation of MobileNetV2
  ☆85Updated 7 years ago
• Orion34-lanbo / tvm-batch-matmul-example
  ☆24Updated 7 years ago
• luhaofang / CACU
  This is a deep learning framework for cnn which using xnor method to accelerate calculating convolution layer on cpu.
  ☆87Updated 8 years ago
• msnqqer / ShuffleNet
  This is a caffe implementation of ShuffleNet model
  ☆15Updated 7 years ago
• manutdzou / faster-rcnn-pure-c-plus-implement
  c++ proposal layer and c plus wrapper
  ☆51Updated 6 years ago
• gudovskiy / ShiftCNN
  A script to convert floating-point CNN models into generalized low-precision ShiftCNN representation
  ☆56Updated 8 years ago
• deepsemantic / quantized_neural_network
  The quantization of CNN/LSTM
  ☆11Updated 8 years ago
• mz24cn / clnet
  OpenCL for Nets - A Deep Learning Framework based on OpenCL, written by C++. Supports popular MLP, RNN(LSTM), CNN(ResNet). Friendly debug…
  ☆68Updated 6 years ago
• miaow1988 / SqueezeNet_v1.2
  Top-1 Acc=61.0% on ImageNet, without any sacrificing compared with SqueezeNet v1.1.
  ☆22Updated 8 years ago
• n3011 / Inception_v3_GoogLeNet
  GoogleNet Inception v3
  ☆44Updated 9 years ago
• zhangxinqian / jetsontx2-cross-compilation-using-nnvm-and-tvm
  nnvm&tvm example of cross compilation and deployment in Nvidia Jetson TX2 platform
  ☆11Updated 7 years ago
• hukim93 / BWN-XNOR-caffe
  Binary Weight Network and XNOR Network.
  ☆63Updated 9 years ago
• lyuchuny3 / Tengine_gemm_tutorial
  Tengine gemm tutorial, step by step
  ☆13Updated 4 years ago