* fix step rnn model run bugs test=develop

* add shell file to automatically build and collect publish result test=develop
* modify API inference of model_optimize_tool and add option for tiny&full publish test=develop

* [python api] init add python api test=develop

* init: delete feed and fetch op, using zero copy
test=develop

* delete the unused test
test=develop

* move the method of SetThread and SetPowerMode from MobileConfig into ConfigBase 
* cxxPredictor will support SetThread and SetPowerMode method

* add conv int8 support(in condition which the input or output channel not be the times of 4)
add add_kernel for cuda.

* can run yolov3 fp32
test=develop

* 1. fix bug with yolov3 run
test=develop