-
Pre-built libraries for InferenceHelper ( https://github.com/iwatake2222/InferenceHelper )
-
TensorFlow Lite : https://github.com/tensorflow/tensorflow
- Options:
- with XNNPACK delegate (x64 and aarch64 only)
- with GPU delegate (Android only)
- with NNAPI delegate (Android only)
- Targets:
- Linux (x64)
- Linux (aarch64)
- Linux (armv7)
- Linux (Android arm64-v8a)
- Linux (Android armeabi-v7a)
- Windows (Visual Studio 2019)
-
Edge TPU : https://github.com/google-coral/libedgetpu
- Targets:
- Linux (x64)
- Linux (aarch64)
- Linux (armv7)
- Windows (Visual Studio 2019)
-
MNN : https://github.com/alibaba/MNN
- Options:
- with / without Vulkan
- Targets:
- Linux (x64)
- Linux (aarch64)
- Linux (armv7)
- Linux (Android arm64-v8a)
- Linux (Android armeabi-v7a)
- Windows (Visual Studio 2019)
-
Arm NN : https://github.com/ARM-software/armnn
- Targets:
- Linux (aarch64)
- Linux (armv7)
-
As for the following frameworks, the official provides pre-built libraries
- ncnn : https://github.com/Tencent/ncnn
- SNPE (Snapdragon Neural Processing Engine SDK) : https://developer.qualcomm.com/software/qualcomm-neural-processing-sdk/tools
- OpenCV : https://github.com/opencv/opencv
- OpenVINO : https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit-download.html
- NNabla : https://github.com/sony/nnabla