To be used with darknet crate.
If you want to build from this repo, run git submodule init && git submodule update --recursive
to get all submodules.
Terms used:
darknet-sys, darknet = Rust wrappers
libdarknet = C/C++ darknet implementation
By default, darknet-sys will compile and link libdarknet statically. You can control the feature flags to change the behavior.
enable-cuda
: Enable CUDA (expects CUDA 10.x and cuDNN 7.x).enable-cudnn
: Enable cuDNNenable-opencv
: Enable OpenCV.enable-openmp
: Enable OpenMP in darknet. Used for parallelization when running on the CPU. Enabled by default.runtime
: Link to libdarknet dynamic library. For example,libdark.so
on Linux.dylib
: Build dynamic library instead of staticbuildtime-bindgen
: Generate bindings from libdarknet headers.
cargo build
You can optionally enable CUDA and OpenCV features. Please read Build with CUDA for more info.
cargo build --features enable-cuda,enable-opencv
If you want to build with custom libdarknet source, point DARKNET_SRC
environment variable to your source path. It should contain CMakeLists.txt
.
export DARKNET_SRC=/path/to/your/darknet/repo
cargo build
With runtime
feature, darknet-sys will not compile libdarknet source code and instead links to libdarknet dynamically. If you are using Linux, make sure libdark.so
is installed on your system.
cargo build --feature runtime
With buildtime-bindgen
feature, darknet-sys re-generates bindings from headers. The option is necessary only when darkent is updated or modified.
If you want to use your (possibly modified) header files, point DARKNET_INCLUDE_PATH
environment variable to your header dir.
Please check that both CUDA 10.x and cuDNN 7.x are installed.
darknet reads CUDA_PATH
environment variable (which defaults to /opt/cuda
if not set) and assumes it can find cuda libraries at ${CUDA_PATH}/lib64
.
export CUDA_PATH=/usr/local/cuda-10.1
cargo build --features enable-cuda
You can also set CUDA_ARCHITECTURES
which is passed to libdarknet's cmake. It defaults to Auto
, which auto-detects GPU architecture based on card present in the system during build.
MIT license.
Huge thanks to all contributors!