Tengine Lite release v1.2-pre

• Tengine-Lite 将开放第一个 NPU 版本给到广大的开发者试用
  • 目前我们 Pre-Release 的是 Amlogic 的一颗带 NPU 的芯片 A311D，合作方式是在 Single Board Computer(SBC)-Khadas vim3上预装此试用版本-传送门；
  • 为了配合预装版本的发布，需要在开源社区开放相应的模型转换工具和模型量化工具；
  • 由于涉及第三方知识产权的问题，暂时还无法开源相关源代码；
  • 欢迎大家尝试在 Khadas VIM3（311D） 上试用 Tengine Lite 所支持的 NPU 最新特性；
  • 闲来大佬打造的真-异构计算（闲来大佬甚至还自己做了个3D打印外壳-传送门)；
  • 欢迎大家提出宝贵的建议，可以来我们 QQ 群交流！
• 我们也在和更多的开源开发板、SBC 公司合作，会有其他开发板，敬请期待；
• 我们也在同更多的 NPU 厂商合作，欢迎感兴趣的小伙伴咨询或加入我们共建 Tengine 开源生态！

Tengine Lite release v1.0

Release v1.0

New feature

• Dynamic graph segmentation

• C++ API (experiment)

• Python API (experiment)

• support ARM-Mali GPU with ACL

• support others GPU with Vulkan (experiment)

• support fp16 inference with armv8.2 (experiment)

New network support

• landmark
• yolact
• openpose
• yolov4

New operator support

• uint8 reference op (experiment)

• mish activation op

Performance

• update the performance of openmp

lite-v0.1

Initial Tengine Lite release v0.1

v1.12.0

Former-commit-id: f2437b875bddf0ae067a072c97bf44eca5f575de

Separate tengine serializer into tengine-module

Former-commit-id: 8989e86c70ab67fff23e4aaf4435cbd48251ba2b

v1.3.2

Separate cpu operator implementation and the framework into two so.
Add serializer for TFLite, and reference implementation on TFLite op.
Add RNN/GRU/LSTM reference implementation

Release 1.0.0

With the new API 2.0 and a few new features and bug fixes.

v0.8.0

Android build to run ACL
MSSD can use GPU to accelerate
Android build with c++_shared instead of gnustl_shared

v0.7.2

Support GPU fp16. Only works with ACL 18.05
More tensorflow model and onnx model support

Release 0.5

This is a first version which implements many basic features for an inference engine