To install this package, run the following command in your project directory.

buckaroo install tiny-dnn/tiny-dnn

Learn More

Read Me

Maintainers Wanted

The project may be abandoned since the maintainer(s) are just looking to move on. In the case anyone is interested in continuing the project, let us know so that we can discuss next steps.

Please visit:!forum/tiny-dnn-dev

Join the chat at Docs License Coverage Status

tiny-dnn is a C++14 implementation of deep learning. It is suitable for deep learning on limited computational resource, embedded systems and IoT devices.

Linux/Mac OSWindows
Build StatusBuild status

Table of contents

Check out the documentation for more info.

What's New


  • Reasonably fast, without GPU:
    • With TBB threading and SSE/AVX vectorization.
    • 98.8% accuracy on MNIST in 13 minutes training (@Core i7-3520M).
  • Portable & header-only:
    • Runs anywhere as long as you have a compiler which supports C++14.
    • Just include tiny_dnn.h and write your model in C++. There is nothing to install.
  • Easy to integrate with real applications:
    • No output to stdout/stderr.
    • A constant throughput (simple parallelization model, no garbage collection).
    • Works without throwing an exception.
    • Can import caffe's model.
  • Simply implemented:
    • A good library for learning neural networks.

Comparison with other libraries

Please see wiki page.

Supported networks


  • core
    • fully connected
    • dropout
    • linear operation
    • zero padding
    • power
  • convolution
    • convolutional
    • average pooling
    • max pooling
    • deconvolutional
    • average unpooling
    • max unpooling
  • normalization
    • contrast normalization (only forward pass)
    • batch normalization
  • split/merge
    • concat
    • slice
    • elementwise-add

activation functions

  • tanh
  • asinh
  • sigmoid
  • softmax
  • softplus
  • softsign
  • rectified linear(relu)
  • leaky relu
  • identity
  • scaled tanh
  • exponential linear units(elu)
  • scaled exponential linear units (selu)

loss functions

  • cross-entropy
  • mean squared error
  • mean absolute error
  • mean absolute error with epsilon range

optimization algorithms

  • stochastic gradient descent (with/without L2 normalization)
  • momentum and Nesterov momentum
  • adagrad
  • rmsprop
  • adam
  • adamax


Nothing. All you need is a C++14 compiler (gcc 4.9+, clang 3.6+ or VS 2015+).


tiny-dnn is header-only, so there's nothing to build. If you want to execute sample program or unit tests, you need to install cmake and type the following commands:


Then change to examples directory and run executable files.

If you would like to use IDE like Visual Studio or Xcode, you can also use cmake to generate corresponding files:

cmake . -G "Xcode"            # for Xcode users
cmake . -G "NMake Makefiles"  # for Windows Visual Studio users

Then open .sln file in visual studio and build(on windows/msvc), or type make command(on linux/mac/windows-mingw).

Some cmake options are available:

optionsdescriptiondefaultadditional requirements to use
USE_TBBUse Intel TBB for parallelizationOFF1Intel TBB
USE_OMPUse OpenMP for parallelizationOFF1OpenMP Compiler
USE_SSEUse Intel SSE instruction setONIntel CPU which supports SSE
USE_AVXUse Intel AVX instruction setONIntel CPU which supports AVX
USE_AVX2Build tiny-dnn with AVX2 library supportOFFIntel CPU which supports AVX2
USE_NNPACKUse NNPACK for convolution operationOFFAcceleration package for neural networks on multi-core CPUs
USE_OPENCLEnable/Disable OpenCL support (experimental)OFFThe open standard for parallel programming of heterogeneous systems
USE_LIBDNNUse Greentea LibDNN for convolution operation with GPU via OpenCL (experimental)OFFAn universal convolution implementation supporting CUDA and OpenCL
USE_SERIALIZEREnable model serializationON2-
USE_DOUBLEUse double precision computations instead of single precisionOFF-
USE_ASANUse Address SanitizerOFFclang or gcc compiler
USE_IMAGE_APIEnable Image API supportON-
USE_GEMMLOWPEnable gemmlowp supportOFF-
BUILD_TESTSBuild unit testsOFF3-
BUILD_EXAMPLESBuild example projectsOFF-
BUILD_DOCSBuild documentationOFFDoxygen
PROFILEBuild unit testsOFFgprof

1 tiny-dnn use C++14 standard library for parallelization by default.

2 If you don't use serialization, you can switch off to speedup compilation time.

3 tiny-dnn uses Google Test as default framework to run unit tests. No pre-installation required, it's automatically downloaded during CMake configuration.

For example, type the following commands if you want to use Intel TBB and build tests:


Customize configurations

You can edit include/config.h to customize default behavior.


Construct convolutional neural networks

#include "tiny_dnn/tiny_dnn.h"
using namespace tiny_dnn;
using namespace tiny_dnn::activation;
using namespace tiny_dnn::layers;

void construct_cnn() {
    using namespace tiny_dnn;

    network<sequential> net;

    // add layers
    net << conv(32, 32, 5, 1, 6) << tanh()  // in:32x32x1, 5x5conv, 6fmaps
        << ave_pool(28, 28, 6, 2) << tanh() // in:28x28x6, 2x2pooling
        << fc(14 * 14 * 6, 120) << tanh()   // in:14x14x6, out:120
        << fc(120, 10);                     // in:120,     out:10

    assert(net.in_data_size() == 32 * 32);
    assert(net.out_data_size() == 10);

    // load MNIST dataset
    std::vector<label_t> train_labels;
    std::vector<vec_t> train_images;

    parse_mnist_labels("train-labels.idx1-ubyte", &train_labels);
    parse_mnist_images("train-images.idx3-ubyte", &train_images, -1.0, 1.0, 2, 2);

    // declare optimization algorithm
    adagrad optimizer;

    // train (50-epoch, 30-minibatch)
    net.train<mse, adagrad>(optimizer, train_images, train_labels, 30, 50);

    // save"net");

    // load
    // network<sequential> net2;
    // net2.load("net");

Construct multi-layer perceptron (mlp)

#include "tiny_dnn/tiny_dnn.h"
using namespace tiny_dnn;
using namespace tiny_dnn::activation;
using namespace tiny_dnn::layers;

void construct_mlp() {
    network<sequential> net;

    net << fc(32 * 32, 300) << sigmoid() << fc(300, 10);

    assert(net.in_data_size() == 32 * 32);
    assert(net.out_data_size() == 10);

Another way to construct mlp

#include "tiny_dnn/tiny_dnn.h"
using namespace tiny_dnn;
using namespace tiny_dnn::activation;

void construct_mlp() {
    auto mynet = make_mlp<tanh>({ 32 * 32, 300, 10 });

    assert(mynet.in_data_size() == 32 * 32);
    assert(mynet.out_data_size() == 10);

For more samples, read examples/main.cpp or MNIST example page.


Since deep learning community is rapidly growing, we'd love to get contributions from you to accelerate tiny-dnn development! For a quick guide to contributing, take a look at the Contribution Documents.


[1] Y. Bengio, Practical Recommendations for Gradient-Based Training of Deep Architectures. arXiv:1206.5533v2, 2012

[2] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86, 2278-2324.

Other useful reference lists:


The BSD 3-Clause License

Gitter rooms

We have gitter rooms for discussing new features & QA. Feel free to join us!