Fix compile issue with ncnn2int8

* [WIP] add reduce op support for onnx

* extend reduction to support 1,2-dim reduction and keepdims

* fix compile error

* split type to 3 flags && split keepdims to another function

* Update CMakeLists.txt

enable quant

* fix opencv compatibility issue with major higher than 2

* constraint input value to [-127, +127]

* keep new line at the end

* rename ncnn snapshot png file

* add NNIE ImageWatch plugin and working snapshot

* add NNIE support to README.md

* fix image path

asymmetric padding parameter for convolution and deconvolution family

* CMake improvement

* Fix bugs

* Fix typo

* Propagate vulkan dependency

* import vulkan

* add config files, now exported target cmake should be able to find packages

* Propagate no-rtti and no-exception

* Provide a option to control rtti and exception in mobile platform

* Make cmake clean

* Resolve conflicts

* Update CMake
PIE is propagated by INTERFACE_POSITION_INDEPENDENT_CODE

* Remove bad things

* add relative README_CN.md;
* obtain time cost with op->forward().

* initial the ncnn post training quantization tools

* clear some comments of tools

* fix the Travis ci compiler error