DeepDetect (http://www.deepdetect.com/) is a machine learning API and server written in C++11. 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
- distributed gradient boosting library XGBoost
- the deep learning and other usages library Tensorflow
- clustering with T-SNE
| Training | Prediction | Classification | Object Detection | Segmentation | Regression | Autoencoder | OCR / Seq2Seq | |
|---|---|---|---|---|---|---|---|---|
| Caffe | Y | Y | Y | Y | Y | Y | Y | Y |
| Caffe2 | Y | Y | Y | Y | N | N | N | N |
| XGBoost | Y | Y | Y | N | N | Y | N/A | N |
| Tensorflow | N | Y | Y | N | N | N | N | N |
| T-SNE | Y | N/A | N/A | N/A | N/A | N/A | N/A | N |
| Dlib | N | Y | Y | Y | N | N | N | N |
| Training | Prediction | |
|---|---|---|
| Caffe | Y | Y |
| Caffe2 | Y | Y |
| XGBoost | Y | Y |
| Tensorflow | N | Y |
| T-SNE | Y | N |
| Dlib | N | Y |
| CSV | SVM | Text words | Text characters | Images | |
|---|---|---|---|---|---|
| Caffe | Y | Y | Y | Y | Y |
| Caffe2 | N | N | N | N | Y |
| XGBoost | Y | Y | Y | N | N |
| Tensorflow | N | N | N | N | Y |
| T-SNE | Y | N | N | N | Y |
| Dlib | N | N | N | N | Y |
| (*) more input support for T-SNE is pending |
DeepDetect implements support for supervised and unsupervised deep learning of images, text and other data, with focus on simplicity and ease of use, test and connection into existing applications. It supports classification, object detection, segmentation, regression, autoencoders, ...
Please join either the community on Gitter or on IRC Freenode #deepdetect, where we help users get through with installation, API, neural nets and connection to external applications.
The reference platforms with support are Ubuntu 14.04 LTS and Ubuntu 16.04 LTS.
Supported images that come with pre-trained image classification deep (residual) neural nets:
-
docker images for CPU and GPU machines are available at https://hub.docker.com/r/beniz/deepdetect_cpu/ and https://hub.docker.com/r/beniz/deepdetect_gpu/ respectively. See https://github.com/beniz/deepdetect/tree/master/docker/README.md for details on how to use them.
-
For Amazon AMI see official builds documentation at https://deepdetect.com/products/ami/, and direct links to GPU AMI and CPU AMI.
See https://github.com/jolibrain/dd_performances for a report on performances on NVidia Desktop and embedded GPUs, along with Raspberry Pi 3.
Setup an image classifier API service in a few minutes: http://www.deepdetect.com/tutorials/imagenet-classifier/
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/
Current features include:
- high-level API for machine learning and deep learning
- support for Caffe, Tensorflow, XGBoost and T-SNE
- classification, regression, autoencoders, object detection, segmentation
- JSON communication format
- remote Python client library
- dedicated server with support for asynchronous training calls
- high performances, benefit from multicore CPU and GPU
- built-in similarity search via neural embeddings
- 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
- connector to handle SVM file format for sparse data
- 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, ResNet, convnet, character-based convnet, mlp, logistic regression)
- support for sparse features and computations on both GPU and CPU
- built-in similarity indexing and search of predicted features and probability distributions
- Full documentation is available from http://www.deepdetect.com/overview/introduction/
- API documentation is available from http://www.deepdetect.com/api/
- FAQ is available from http://www.deepdetect.com/overview/faq/
- Python client:
- REST client: https://github.com/beniz/deepdetect/tree/master/clients/python
- 'a la scikit' bindings: https://github.com/ArdalanM/pyDD
- Javacript client: https://github.com/jolibrain/deepdetect-js
- Java client: https://github.com/kfadhel/deepdetect-api-java
- Early C# client: https://github.com/beniz/deepdetect/pull/98
- Log DeepDetect training metrics via Tensorboard with dd_board
- 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);
- CUDA 9 or 8 is recommended for GPU mode.
- BLAS via ATLAS, MKL, or OpenBLAS.
- protobuf
- IO libraries hdf5, leveldb, snappy, lmdb
None outside of C++ compiler and make
- CUDA 8 is recommended for GPU mode.
- Cmake > 3
- Bazel 0.8.x
- CUDA 8 and cuDNN 7 for GPU mode
By default DeepDetect automatically relies on a modified version of Caffe, https://github.com/beniz/caffe/tree/master This version includes many improvements over the original Caffe, such as sparse input data support, exception handling, class weights, object detection, segmentation, and various additional losses and layers.
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.
-
Image classification Web interface: HTML and javascript classification image demo in demo/imgdetect
-
Image similarity search: Python script for indexing and searching images is in demo/imgsearch
-
Image object detection: Python script for object detection within images is in demo/objdetect
-
Image segmentation: Python script for image segmentation is in demo/segmentation
- List of examples, from MLP for data, text, multi-target regression to CNN and GoogleNet, finetuning, etc...: http://www.deepdetect.com/overview/examples/
More models:
- List of free, even for commercial use, deep neural nets for image classification, and character-based convolutional nets for text classification: http://www.deepdetect.com/applications/list_models/
DeepDetect comes with a built-in system of neural network templates (Caffe backend only at the moment). This allows the creation of custom networks based on recognized architectures, for images, text and data, and with much simplicity.
Usage:
- specify
templateto use, frommlp,convnetandresnet - specify the architecture with the
layersparameter:- for
mlp, e.g.[300,100,10] - for
convnet, e.g.["1CR64","1CR128","2CR256","1024","512"], where the main pattern isxCRywhereyis the number of outputs (feature maps),CRstands for Convolution + Activation (withreluas default), andxspecifies the number of chainedCRblocks without pooling. Pooling is applied between allxCRy`
- for
- for
resnets:- with images, e.g.
["Res50"]where the main pattern isResXwith X the depth of the Resnet - with character-based models (text), use the
xCRypattern of convnets instead, with the main difference thatxnow specifies the number of chainedCRblocks within a resnet block - for Resnets applied to CSV or SVM (sparse data), use the
mlppattern. In this latter case, at the moment, theresnetis built with blocks made of two layers for each specified layer after the first one. Here is an example:[300,100,10]means that a first hidden layer of size300is applied followed by aresnetblock made of two100fully connected layer, and another block of two10fully connected layers. This is subjected to future changes and more control.
- with images, e.g.
DeepDetect is designed and implemented by Emmanuel Benazera [email protected].
Below are instructions for Ubuntu 14.04 LTS. For other Linux and Unix systems, steps may differ, CUDA, Caffe and other libraries may prove difficult to setup. If you are building on 16.04 LTS, look at https://github.com/beniz/deepdetect/issues/126 that tells you how to proceed.
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 libboost-iostreams-dev libcurlpp-dev libcurl4-openssl-dev protobuf-compiler libopenblas-dev libhdf5-dev libprotobuf-dev libleveldb-dev libsnappy-dev liblmdb-dev libutfcpp-dev cmake libgoogle-perftools-dev unzip python-setuptools python-dev libspdlog-dev python-six python-enum34
For compiling along with Caffe:
mkdir build
cd 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
To target the build of underlying Caffe to a specific CUDA architecture (e.g. Pascal), you can use:
cmake .. -DCUDA_ARCH="-gencode arch=compute_61,code=sm_61"
If you would like to build on NVidia Jetson TX1:
cmake .. -DCUDA_ARCH="-gencode arch=compute_53,code=sm_53" -DUSE_CUDNN=ON -DJETSON=ON -DCUDA_USE_STATIC_CUDA_RUNTIME=OFF
On Jetson TX2, use -DCUDA_ARCH="-gencode arch=compute_62,code=sm_62"
If you would like a CPU only build, use:
cmake .. -DUSE_CPU_ONLY=ON
If you would like to constrain Caffe to CPU only, use:
cmake .. -DUSE_CAFFE_CPU_ONLY=ON
If you would like to build with XGBoost, include the -DUSE_XGBOOST=ON parameter to cmake:
cmake .. -DUSE_XGBOOST=ON
If you would like to build the GPU support for XGBoost (experimental from DMLC), use the -DUSE_XGBOOST_GPU=ON parameter to cmake:
cmake .. -DUSE_XGBOOST=ON -DUSE_XGBOOST_GPU=ON
First you must install Bazel and Cmake with version > 3.
And other dependencies:
sudo apt-get install python-numpy swig python-dev python-wheel unzip
If you would like to build with Tensorflow, include the -DUSE_TF=ON paramter to cmake:
cmake .. -DUSE_TF=ON -DCUDA_USE_STATIC_CUDA_RUNTIME=OFF
If you would like to constrain Tensorflow to CPU, use:
cmake .. -DUSE_TF=ON -DUSE_TF_CPU_ONLY=ON
You can combine with XGBoost support with:
cmake .. -DUSE_TF=ON -DUSE_XGBOOST=ON
Simply specify the option via cmake command line:
cmake .. -DUSE_TSNE=ON
Specify the following option via cmake:
cmake .. -DUSE_DLIB=ON
This will automatically build with GPU support if possible. Note: this will also enable cuDNN if available by default.
If you would like to constrain Dlib to CPU, use:
cmake .. -DUSE_DLIB=ON -DUSE_DLIB_CPU_ONLY=ON
Specify the option via cmake:
cmake .. -DUSE_CAFFE2=ON
Specify the following option via cmake:
cmake .. -DUSE_SIMSEARCH=ON
Specify the following option via cmake:
cmake .. -DUSE_DD_SYSLOG=ON
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
Run tests with:
ctest
cd build/main
./dede
DeepDetect [ commit 73d4e638498d51254862572fe577a21ab8de2ef1 ]
Running DeepDetect HTTP server on localhost:8080
Main options are:
-hostto select which host to run on, default islocalhost, use0.0.0.0to listen on all interfaces-portto select which port to listen to, default is8080-nthreadsto select the number of HTTP threads, default is10
To see all options, do:
./dede --help
To use deepdetect without the client/server architecture while passing the exact same JSON messages from the API:
./dede --jsonapi 1 <other options>
where <other options> stands for the command line parameters from the command line JSON API:
-info (/info JSON call) type: bool default: false
-service_create (/service/service_name call JSON string) type: string default: ""
-service_delete (/service/service_name DELETE call JSON string) type: string default: ""
-service_name (service name string for JSON call /service/service_name) type: string default: ""
-service_predict (/predict POST call JSON string) type: string default: ""
-service_train (/train POST call JSON string) type: string default: ""
-service_train_delete (/train DELETE call JSON string) type: string default: ""
-service_train_status (/train GET call JSON string) type: string default: ""
The options above can be obtained from running
./dede --help
Example of creating a service then listing it:
./dede --jsonapi 1 --service_name test --service_create '{"mllib":"caffe","description":"classification service","type":"supervised","parameters":{"input":{"connector":"image"},"mllib":{"template":"googlenet","nclasses":10}},"model":{"templates":"/path/to/deepdetect/templates/caffe/","repository":"/path/to/model/"}}'
Note that in command line mode the --service_xxx calls are executed sequentially, and synchronously. Also note the logs are those from the server, the JSON API response is not available in pure command line mode.
See tutorials from http://www.deepdetect.com/tutorials/tutorials/
- DeepDetect (http://www.deepdetect.com/)
- Caffe (https://github.com/BVLC/caffe)
- XGBoost (https://github.com/dmlc/xgboost)
- T-SNE (https://github.com/DmitryUlyanov/Multicore-TSNE)