The developer doc is available on readthedoc.
If you ever want to build it, we provide a dockerfile:
docker build -t sp-docs -f docs/Dockerfile .
docker run -it --rm -v$(pwd):/code sp-docs doxygen
docker run -it --rm -v$(pwd):/code sp-docs make htmlSpleeter is based on tensorflow. As
described in their documentation, we can easily run the inference of such a model in C++.
condainstalled and available in your path- the
tensorflow_cclibrary (see the Help section for instructions)
We base our work on cmake.
mkdir build && cd build
cmake -DTENSORFLOW_CC_INSTALL_DIR=/my/install/dir ..
cmake --build .This will:
- Clone
Spleeterand checkout its release version. - Create the
condaenvironment - Download the pre-trained weights
- Generate each models
- Build the
spleeter++library and its associated tests
We need to match the version used in Spleeter i.e. 1.14.0.
The build system is based on Bazel. Install the right (0.25.2) version found here.
Then, clone the repository and checkout the right tag:
git clone https://github.com/tensorflow/tensorflow.git
cd tensorflow
git checkout v1.14.0 # select the version you want...Install dependencies and configure:
rm BUILD # problem with setup.py os osx
python tensorflow/tools/pip_package/setup.py install
mv build build-bu
git checkout BUILD
./configureThen, build the library (it will take a while...):
bazel build --config=monolithic --jobs=6 --verbose_failures //tensorflow:libtensorflow_cc.soFinally, install everything in a specific folder:
INSTALL_DIR=install
INCLUDE_DIR=$INSTALL_DIR/include
# libraries
mkdir -p $INSTALL_DIR/bin
cp bazel-bin/tensorflow/libtensorflow_cc.so* $INSTALL_DIR/bin/
# and headers
mkdir -p $INSTALL_DIR/include
rsync -a --prune-empty-dirs --include '*/' --include '*.h' --exclude '*' tensorflow/ $INCLUDE_DIR/tensorflow
mkdir -p $INSTALL_DIR/include/third_party/eigen3/unsupported/
cp -r ./bazel-tensorflow/external/eigen_archive/unsupported/Eigen $INSTALL_DIR/include/third_party/eigen3/unsupported/Eigen
cp -r ./bazel-tensorflow/external/eigen_archive/Eigen $INSTALL_DIR/include/third_party/eigen3/Eigen