jnbraun / bcnn

A minimalist Deep Learning framework for embedded Computer Vision

BCNN

Introduction

BCNN (Bare Convolutional Neural Networks) is a minimalist framework designed to prototype, train and deploy convolutional neural networks for embedded computer vision applications.

Features

• Written in C99. Clean C API designed to be integrated in C or C++ codebase.
• Lightweight: the minimal build requires no external dependency.
• Modular: Can leverage a Blas library such as OpenBLAS on CPU. Can also run on Nvidia's GPU. CuDNN is supported to offer maximal speed.
• Fast: Optimized CPU inference speed using AVX and ARM Neon vectorizations and OpenMP multithreading.
• Flexible: Supports multi inputs / outputs / branches. Provides the commonly used operators to build state-of-the-art CNN architectures (ResNet, DenseNet, MobileNet, Yolo ...)
• Command line tool to train / evaluate models via simple configuration file.
• Online data augmentation via bip, a fast image processing library (usable as standalone module).
• (Experimental) Model converters from Caffe -> bcnn and bcnn -> TensorFlow Lite.

Getting started

Download or clone the repository:

git clone https://github.com/jnbraun/bcnn.git

You need to have cmake installed in order to build the library.

[Optional] Dependencies

CPU

• Minimal build: no external dependency.
• Build with Blas: requires a blas library (OpenBLAS is recommended).

GPU

Requires CUDA libraries (cudart, cublas, curand) and a GPU with compute capability 2.0 at least. CuDNN is optional but supported.

Build

• User configuration: Depending on you system, you may want to edit the following lines of the CMakeLists.txt:

# User configuration settings
option(USE_AVX "Build with AVX instructions" ON)
option(USE_CUDA "Build with CUDA libraries" OFF)
option(USE_CUDNN "Build with CuDNN library" OFF)
option(USE_BLAS "Build with BLAS library" ON)
option(USE_NEON "Build with Neon instructions" OFF)
option(USE_OPENMP "Enable OpenMP multithreading" ON)

• [Optional] When building with CUDA and / or CuDNN, you may need to adjust the following line depending on the compute capability of your GPU:

# Uncomment the proper line according to the system cuda arch
set(CUDA_ARCH 
    #"-gencode arch=compute_30,code=sm_30;"
    #"-gencode arch=compute_35,code=sm_35;"
    "-gencode arch=compute_50,code=sm_50;"
    "-gencode arch=compute_50,code=compute_50;"
    "-gencode arch=compute_52,code=sm_52;"
    #"-gencode arch=compute_60,code=sm_60;"
    #"-gencode arch=compute_61,code=sm_61;"
)

• Build

cd path/to/bcnn
mkdir build
cd build/
cmake ../
make

How to use it

• Use the command line tool bcnn-cl with configuration file: see an example here.

• Or use the static library and write your own code: see an example there.

License

Released under MIT license.

bcnn's Issues

Deep learning

Hi
Happy new year!
sorry
I would like to ask something else
what courses did you take and what books did you read on neural networks and deep learning?
can you recommend resources in which development is shown from scratch?
like http://neuralnetworksanddeeplearning.com/

About the Application

Hi, may I know is that any application can apply after run all this codes?

On make I am getting this cblas error.

[ 88%] Linking C executable bin/bcnn-cl
/usr/bin/ld: lib/libbcnn.a(bcnn_conv_layer.c.o): in function bcnn_forward_conv_layer_cpu': bcnn_conv_layer.c:(.text+0x234f): undefined reference to cblas_sgemm'
/usr/bin/ld: lib/libbcnn.a(bcnn_conv_layer.c.o): in function bcnn_backward_conv_layer_cpu': bcnn_conv_layer.c:(.text+0x26f7): undefined reference to cblas_sgemm'
/usr/bin/ld: bcnn_conv_layer.c:(.text+0x27e1): undefined reference to cblas_sgemm' /usr/bin/ld: bcnn_conv_layer.c:(.text+0x284b): undefined reference to cblas_sgemm'
/usr/bin/ld: lib/libbcnn.a(bcnn_fc_layer.c.o): in function bcnn_forward_fullc_layer_cpu': bcnn_fc_layer.c:(.text+0x9bb): undefined reference to cblas_sgemm'
/usr/bin/ld: lib/libbcnn.a(bcnn_fc_layer.c.o):bcnn_fc_layer.c:(.text+0xc29): more undefined references to `cblas_sgemm' follow
collect2: error: ld returned 1 exit status
make[2]: *** [CMakeFiles/bcnn-cl.dir/build.make:93: bin/bcnn-cl] Error 1
make[1]: *** [CMakeFiles/Makefile2:111: CMakeFiles/bcnn-cl.dir/all] Error 2
make: *** [Makefile:84: all] Error 2

Many thanks!

question

sorry can you give your email address or where is it convenient for you to chat? I wanted to ask something about the framework and skills.

Cannot Build with cuda support

Hi Jean,
Thank you very much for your contributions to open source community.
I would like to use bcnn with CUDA support on. when I set them on in CmakeLists.txt

cmake .. ends up with errors.

I have installed cuda and nvcc --version does return following ;

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2018 NVIDIA Corporation
Built on Sat_Aug_25_21:08:01_CDT_2018
Cuda compilation tools, release 10.0, V10.0.130

I suspect this could be because of lacking of maybe some symbolic links ?
Have you met this problem ?