README.md

Menoh

Menoh is DNN inference library with C API.

Menoh is released under MIT License.

DISCLAIMER: Menoh is still experimental. Use it at your own risk. In particular not all operators in ONNX are supported, so please check whether the operators used in your model are supported. We have checked that VGG16 and ResNet50 models converted by onnx-chainer work fine.

Document

This codebase contains C API and C++ API.

Goal

• DNN Inference with CPU
• ONNX support
• Easy to use.

Related Projects

• Chainer model to ONNX : onnx-chainer
• C# wrapper : menoh-sharp
• Go wrapper : go-menoh
  • (unofficial wrapper gomenoh by kou-m san has been merged)
• Haskell wrapper : menoh-haskell
• Node.js wrapper : node-menoh
• Ruby wrapper : menoh-ruby
• Rust wrapper : menoh-rs
  • There is also unofficial Rust wrapper by Y-Nak san
• [Unofficial] ROS interface by Akio Ochiai san : menoh_ros
• [Unofficial] OCaml wrapper by wkwkes san : Menohcaml

Installation using package manager or binary packages

• For Windows users, prebuild libraries are available (see release) and Nuget package is available.
• For macOS user, Homebrew tap repository is available.
• For Ubuntu user, binary packages are available.

  $ curl -LO https://github.com/pfnet-research/menoh/releases/download/v1.1.1/ubuntu1604_mkl-dnn_0.16-1_amd64.deb
  $ curl -LO https://github.com/pfnet-research/menoh/releases/download/v1.1.1/ubuntu1604_menoh_1.1.1-1_amd64.deb
  $ curl -LO https://github.com/pfnet-research/menoh/releases/download/v1.1.1/ubuntu1604_menoh-dev_1.1.1-1_amd64.deb
  $ sudo apt install ./ubuntu1604_*_amd64.deb
  

  If you are using Ubuntu 18.04, please replace 1604 with 1804.

Installation from source

Requirements

• MKL-DNN Library (0.14 or later)
• Protocol Buffers (2.6.1 or later)

Build

Execute following commands in root directory.

python scripts/retrieve_data.py
mkdir build && cd build
cmake ..
make

See BUILDING.md for details.

Installation

Execute following command in build directory created at Build section.

make install

Run VGG16 example

Execute following command in root directory.

./example/vgg16_example_in_cpp

Result is here

vgg16 example
-18.1883 -26.5022 -20.0474 13.5325 -0.107129 0.76102 -23.9688 -24.218 -21.6314 14.2164 
top 5 categories are
8 0.885836 n01514859 hen
7 0.104591 n01514668 cock
86 0.00313584 n01807496 partridge
82 0.000934658 n01797886 ruffed grouse, partridge, Bonasa umbellus
97 0.000839487 n01847000 drake

Please give --help option for details

./example/vgg16_example_in_cpp --help

Run test

Setup chainer

Then, execute following commands in root directory.

python scripts/gen_test_data.py
cd build
cmake -DENABLE_TEST=ON ..
make
./test/menoh_test.out

Current supported operators

Activation functions

• Elu
• LeakyRelu
• Relu
• Softmax
• Tanh

Array manipulations

• Concat

Neural network connections

• Conv
• ConvTranspose
• FC

Mathematical functions

• Abs
• Add
• Sqrt
• Sum

Normalization functions

• BatchNormalization
• LRN

Spatial pooling

• AveragePool
• GlobalAveragePool
• GlobalMaxPool
• MaxPool

License

Menoh is released under MIT License. Please see the LICENSE file for details.

Note: scripts/retrieve_data.py downloads data/VGG16.onnx. data/VGG16.onnx is generated by onnx-chainer from pre-trained model which is uploaded at http://www.robots.ox.ac.uk/%7Evgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel

That pre-trained model is released under Creative Commons Attribution License.