* fix pooling overflow, test=develop

* fix conflict test=develop

int8 direct_conv, dw_conv add relu6 and leaky relu fusion

* improve 3x3s1 direct profile

* add gemv+relu6/lleakyRelu

* fix relu6 problem, test=develop

* fix format, test=develop

* add six / scale , test=develop

* reduce .so size. test=develop

* compile all targets when LITE_ON_TINY_PUBLISH=OFF

* unordered_map is more convenient when key is customized class

* test=develop

* fix pooling bug and speed

* add 2x2s2p1 pooling. test=develop

* fix conflict, test=develop

* add scale+relu/relu6/leakyrelu test=develop
* fix format， test=develop

*Pool2d supports adaptive param

improve sgemm performance on A53

* Add hard_swish, ctc_align and reciprocal op, test=develop
* Move some activation ops to extra, test=develop

* fxi ff, test=develop

* delete bgr_flip, test=develop

* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][ARM] comment assembly of layout armv7 cpu. test=develop

* add backend

* add kernel

* add grad kernel

* improve conv_dw profile with rel relu6 leakyrelu, test=develop

* add depthwise, test=develop

* fix ci error, test=develop

* fix cv demo print, test=develop

* [ARM] improve sgemm performance with relu, relu6 and leakey relu, test=develop

* [ARM] improve sgemm performance with relu, relu6 and leakey relu, test=develop

* fix clang v7 error
* change ut, test=develop
* fix conv ut, test=develop

* set arm_lang default is off. test=develop

* fix resize error, test-develop