keras2c 2.0

A library for converting Keras neural networks to real-time compatible C.

keras2c is a library for deploying keras neural networks in C99, using only standard libraries. It is designed to be as simple as possible for real-time applications.

Please cite this paper if you use this work in your research:

R. Conlin, K. Erickson, J. Abbate, and E. Kolemen, “Keras2c: A library for converting Keras neural networks to real-time compatible C,”
Engineering Applications of Artificial Intelligence, vol. 100, p. 104182, Apr. 2021, doi: 10.1016/j.engappai.2021.104182.

Installation

Recommended Installation

The modern way to install keras2c is via pip:

pip install keras2c

To use the original/stable version, use the Release v1.0.2 (https://github.com/PlasmaControl/keras2c/releases/tag/v1.0.2) with the command:

git clone [e-mail]:PlasmaControl/keras2c.git --branch v1.0.2

For Windows, make sure that you have gcc installed. We recommend CYGWIN with make and gcc.

Quickstart

keras2c can be used from the command line:

python -m keras2c [-h] [-m] [-t] model_path function_name

A library for converting the forward pass (inference) part of a keras model to
    a C function

positional arguments:
  model_path         File path to saved keras .h5 model file
  function_name      What to name the resulting C function

optional arguments:
  -h, --help         show this help message and exit
  -m, --malloc       Use dynamic memory for large arrays. Weights will be
                     saved to .csv files that will be loaded at runtime
  -t , --num_tests   Number of tests to generate. Default is 10

It can also be used within a python environment:

from keras2c import k2c
k2c(model, function_name, malloc=False, num_tests=10, verbose=True)

For more information, see Installation and Usage

Supported Layers

• Core Layers: Dense, Activation, Dropout, Flatten, Input, Reshape, Permute, RepeatVector, ActivityRegularization, SpatialDropout1D, SpatialDropout2D, SpatialDropout3D

• Convolution Layers: Conv1D, Conv2D, Conv3D, Cropping1D, Cropping2D, Cropping3D, UpSampling1D, UpSampling2D, UpSampling3D, ZeroPadding1D, ZeroPadding2D, ZeroPadding3D

• Pooling Layers: MaxPooling1D, MaxPooling2D, AveragePooling1D, AveragePooling2D, GlobalMaxPooling1D, GlobalAveragePooling1D, GlobalMaxPooling2D, GlobalAveragePooling2D, GlobalMaxPooling3D, GlobalAveragePooling3D

• Recurrent Layers: SimpleRNN, GRU, LSTM, SimpleRNNCell, GRUCell, LSTMCell

• Embedding Layers: Embedding

• Merge Layers: Add, Subtract, Multiply, Average, Maximum, Minimum, Concatenate, Dot

• Advanced Activation Layers: LeakyReLU, PReLU, ELU, Softmax, ReLU

• Normalization Layers: BatchNormalization

• Noise Layers: GaussianNoise, GaussianDropout, AlphaDropout

• Layer Wrappers: TimeDistributed, Bidirectional

ToDo

• Core Layers: Lambda, Masking

• Convolution Layers: SeparableConv1D, SeparableConv2D, DepthwiseConv2D, Conv2DTranspose, Conv3DTranspose

• Pooling Layers: MaxPooling3D, AveragePooling3D

• Locally Connected Layers: LocallyConnected1D, LocallyConnected2D

• Recurrent Layers: ConvLSTM2D, ConvLSTM2DCell

• Merge Layers: Broadcasting merge between different sizes

• Misc: models made from submodels

Contribute

• Documentation: https://f0uriest.github.io/keras2c/

• Issue Tracker: https://github.com/f0uriest/keras2c/issues

• Source Code: https://github.com/f0uriest/keras2c/

License

The project is licensed under the LGPLv3 license.