* add quantize model support for trt and paddle
* fix bugs
* fix
* update paddle2onnx version
* update version
* add quantize test
Co-authored-by: Jason <jiangjiajun@baidu.com>
* [cmake] support Android arm64-v8a & armeabi-v7a native c++ sdk
* [cmake] fixed patchelf download on mac and android
* [lite] Add threads and power_mode option support
* [pybind] update runtime pybind for lite power mode
* [python] Add set_lite_power_mode api to runtime
* [Lite] add lite enable_fp16 option support
* [lite] add more options for lite backend.
* [cmake] fixed Paddle Lite typo
* [runtime] format LitePowerMode enum comments
* [runtime] format lite option comments
* [cmake] support Android arm64-v8a & armeabi-v7a native c++ sdk
* [cmake] fixed patchelf download on mac and android
* [lite] Add threads and power_mode option support
* [pybind] update runtime pybind for lite power mode
* [python] Add set_lite_power_mode api to runtime
* Add OPENCV_DIRECTORY option to provide the ability to specify the installed opecv lib pat
* Use find_package for opencv in windows, mac and linux
* Fix opencv cmake
* Fix python lib rpath setting
* fix mac python package
* Add some promt when use different opencv lib
* add status message
* Fix the backslash
* Fix python package user defined libs
* Fix windows python process libs
* Add windows lib set path
* add fastdeploy.text.UIEModel
* Add uie python example
* Add one schema for cpp demo
* Add ConvertUIEResultToDict for pretty the uie result in python
* remove default args for SchemaNode
* Add uie example args
* Add uie python api desc
* Add infer.py usage
* truncate some example output
* Add uie schema usage
* Add uie result md
* Add uie c++ api doc