- mobile-deep-learning_mod_v2_success.rar
(origin) 《移动深度学习》
(origin) https://github.com/allonli/mobile-deep-learning
Key code : if defined(MDL_V7)
https://github.com/allonli/mobile-deep-learning/blob/master/src/math/gemm.cpp
- mace_android_demo_v6_fast.rar
(origin) https://github.com/XiaoMi/mace
(origin) https://mace.readthedocs.io/en/latest/introduction.html - (TODO) https://github.com/zhy520xp/mace-makefile-project
- (TODO) https://github.com/conansherry/easy_mace
- (TOOD) https://github.com/conansherry/convert_model
- (TODO) https://github.com/huuuuusy/Xiaomi-MACE-Notes
- (TODO) https://github.com/qinRight/macelibrary
- (TODO) mcu version
- 英文文档
https://blog.csdn.net/asonle/article/details/80869518
https://mace.readthedocs.io/en/latest/index.html
https://buildmedia.readthedocs.org/media/pdf/mace/latest/mace.pdf
- mnndemo_v2_no_jni_success.rar
(origin) https://github.com/alibaba/MNN
(origin) https://www.yuque.com/mnn/cn/build_android
- tnndemo_v1_slow.rar
(origin) https://github.com/Tencent/TNN
- squeezencnn_v1.rar
(origin) https://github.com/Tencent/ncnn - NCNN使用总结
https://blog.csdn.net/u011046017/article/details/92849082
- himindsporedemo_v2_success.rar
(origin) image_classification
https://download.mindspore.cn/model_zoo/official/lite/mobilenetv2_openimage_lite/
https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/lite/image_classification
https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.0/lite/android_aarch64/mindspore-lite-1.0.0-minddata-arm64-cpu.tar.gz
https://ms-release.obs.cn-north-4.myhuaweicloud.com/1.0.0/lite/android_aarch32/mindspore-lite-1.0.0-minddata-arm32-cpu.tar.gz
- paddlelitedemo_v1_success.rar
(origin) Paddle-Lite-Demo
https://github.com/PaddlePaddle/Paddle-Lite-Demo
https://paddle-lite.readthedocs.io/zh/latest/demo_guides/android_app_demo.html
(model) https://paddlelite-demo.bj.bcebos.com/models/ssd_mobilenet_v1_fp32_224_for_cpu_v2_6_0.tar.gz
(so) https://paddle-lite.readthedocs.io/zh/latest/quick_start/release_lib.html
(so) https://paddlelite-data.bj.bcebos.com/Release/2.6.1/Android/inference_lite_lib.android.armv7.gcc.c++_shared.CV_OFF.tar.gz
(demo) https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/b6c36ecfdc0ad6f500c72b40c8b0c67916421ab9/PaddleLite-android-demo/object_detection_demo
- tenginelitedemo_v3_success_ssd.rar
(origin) https://github.com/OAID/Tengine
(model) search baidupan, Tengine-models/赏金任务模型/mobilenet_ssd.tmfile
use LOCAL_WHOLE_STATIC_LIBRARIES - 官网资料下载
http://www.tengine.org.cn/info.php?class_id=105105
http://www.eaidk.com/info.php?class_id=102&bz=1
- tflitedemo_v1_success.rar
(origin) https://tensorflow.google.cn/lite/models/image_classification/overview?hl=zh_cn
(origin) https://tensorflow.google.cn/lite/guide/hosted_models?hl=zh_cn
- pytorchmobiledemo_v1_success.rar
(origin) https://github.com/pytorch/android-demo-app/tree/master/NativeApp
(origin) https://pytorch.org/tutorials/recipes/android_native_app_with_custom_op.html
(origin) https://pytorch.org/mobile/android/#api-docs
- (origin) https://github.com/ARM-software/armnn
https://review.mlplatform.org/admin/repos/ml/armnn
git clone "https://review.mlplatform.org/ml/armnn" - Arm NN Quantised Mobilenet
https://github.com/ARM-software/ML-examples/blob/master/armnn-mobilenet-quant/README.md
ML-examples
https://github.com/ARM-software/ML-examples - Arm NN MNIST
https://developer.arm.com/technologies/machine-learning-on-arm/developer-material/how-to-guides/
https://github.com/ARM-software/ML-examples/blob/master/armnn-mnist/README.md
https://github.com/pytorch/QNNPACK
https://github.com/pytorch/pytorch/tree/master/aten/src/ATen/native/quantized/cpu/qnnpack
https://github.com/in66-dev/In-Prestissimo
https://github.com/Tencent/FeatherCNN
https://github.com/JDAI-CV/DNNLibrary
https://github.com/daquexian/dnnlibrary-example
https://github.com/Oneflow-Inc/oneflow
Android 8.1 NNAPI 评测以及可能是全球第一个的 NNAPI 库
https://zhuanlan.zhihu.com/p/30926958