C++实现的基于外部机器学习/深度学习库：deepdetect

jopen 8年前

</a>DeepDetect是C++实现的基于外部机器学习/深度学习库（目前是Caffe）的API。给出了图片训练（ILSVRC）和文本训练（基于字的情感分析，NIPS15）的样例，以及根据图片标签索引到ElasticSearch中。DeepDetect (http://www.deepdetect.com/) 是一个机器学习API和服务器，采用 C++11开发。It makes state of the art machine learning easy to work with and integrate into existing applications.

DeepDetect relies on external machine learning libraries through a very generic and flexible API. At the moment it has support for the deep learning library Caffe.

Main functionalities:

DeepDetect implements support for supervised deep learning of images and other data, with focus on simplicity and ease of use, test and connection into existing applications.

Quickstart

Setup an image classifier API service in a few minutes: http://www.deepdetect.com/tutorials/imagenet-classifier/

Tutorials

List of tutorials, training from text, data and images, setup of prediction services, and export to external software (e.g. ElasticSearch): http://www.deepdetect.com/tutorials/tutorials/

Features and Documentation

Current features include:

  • high-level API for machine learning
  • JSON commnunication format
  • remote Python client library
  • dedicated server with support for asynchronous training calls
  • high performances, benefit from multicores and GPU
  • connector to handle large collections of images with on-the-fly data augmentation (e.g. rotations, mirroring)
  • connector to handle CSV files with preprocessing capabilities
  • connector to handle text files, sentences, and character-based models
  • range of built-in model assessment measures (e.g. F1, multiclass log loss, ...)
  • no database dependency and sync, all information and model parameters organized and available from the filesystem
  • flexible template output format to simplify connection to external applications
  • templates for the most useful neural architectures (e.g. Googlenet, Alexnet, convnet, character-based convnet, mlp, logistic regression)
Documentation
Dependencies
  • C++, gcc >= 4.8 or clang with support for C++11 (there are issues with Clang + Boost)
  • eigen for all matrix operations;
  • glog for logging events and debug;
  • gflags for command line parsing;
  • OpenCV >= 2.4
  • cppnetlib
  • Boost
  • curl
  • curlpp
  • utfcpp
  • gtest for unit testing (optional);
Caffe Dependencies
  • CUDA 7 or 6.5 is required for GPU mode.
  • BLAS via ATLAS, MKL, or OpenBLAS.
  • protobuf
  • IO libraries hdf5, leveldb, snappy, lmdb
Caffe version

By default DeepDetect automatically relies on a modified version of Caffe, https://github.com/beniz/caffe/tree/master_dd_integ

Implementation

The code makes use of C++ policy design for modularity, performance and putting the maximum burden on the checks at compile time. The implementation uses many features from C++11.

Visual Demo

HTML and javascript classification image demo in demo/imgdetect

Examples
Models

Authors

DeepDetect is designed and implemented by Emmanuel Benazera beniz@droidnik.fr.

Build

Below are instructions for Linux systems.

Beware of dependencies, typically on Debian/Ubuntu Linux, do:

sudo apt-get install build-essential libgoogle-glog-dev libgflags-dev libeigen3-dev libopencv-dev libcppnetlib-dev libboost-dev libcurlpp-dev libcurl4-openssl-dev protobuf-compiler libopenblas-dev libhdf5-dev libprotobuf-dev libleveldb-dev libsnappy-dev liblmdb-dev libutfcpp-dev

For compiling along with Caffe:

mkdir build  cmake ..  make

If you are building for one or more GPUs, you may need to add CUDA to your ld path:

export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda/lib64

If you would like to build with cuDNN, your cmake line should be:

cmake .. -DUSE_CUDNN=ON

Run tests

Note: running tests requires the automated download of ~75Mb of datasets, and computations may take around thirty minutes on a CPU-only machines.

To prepare for tests, compile with:

cmake -DBUILD_TESTS=ON ..  make

Start the server

cd build/main  ./dede    DeepDetect [ commit 73d4e638498d51254862572fe577a21ab8de2ef1 ]  Running DeepDetect HTTP server on localhost:8080

Run examples

See tutorials from http://www.deepdetect.com/tutorials/tutorials/

References

项目地址： https://github.com/beniz/deepdetect/