* rm grad code

* add mul_grad, test=develop

* add strip lib in ios

* add strip lib in ios test=develop

* fix memory leaky, test=develop

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

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][CMAKE] fix cmake for opencl tiny_pubish compile. test=develop

* Fix OpenCL kernel of exp, tanh,

* Fix layout pass for opencl backend,

* Add how to debug cl kernel. test=develop.

This reverts commit 670fcc3c.

add cuda c++ doc

*fix yuv resize bug, test=develop

* fix format, test=develop

* fix build error, test=develop

* fix resize, test=develop

* move anakin rst, test=develop

- 增加cuda c++ demo.
- 考虑到检测模型尾部一般是multiclass_nms，该kernel为host，如果fetch kernel为cuda的话，则会在此处插入无用的io_copy(host->cuda)，由于该原因，注释掉fetch的cuda kernel. 默认使用host的fetch kernel. 此处暗中进行的行为：每次predictor run完，都会默认把数据从cuda拷贝到cpu

* * support download bm_sdk, test=develop

* [LITE][BM] add slice op

* [LITE][BM] fix concat issue

* [LITE][BM] support reduce full ops, test=develop

* [LITE][BM] change test_resnet50 to change test_classify

* [LITE][BM] add cast op

* [LITE][BM] add reduce and other ops, test=develop

* [LITE][BM] add reduce,cast and other ops, test=develop

* feature: buffer sharing, test=develop

* fix the warning of buffer.h, test=develop

* test cuda only if necessary, test=develop

add cuda ci.

Organize cuda compilation products.

* add sgd op, test=develop

* 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

* [NPU] subgraph's precision register to kAny

* fix conv 2-pad to 4-pad

* fix compute conv shape

* fix pad, test=develop

* change conv_depthwise_3x3s1_fp.cc name to conv3x3s1p01_depthwise_fp32.cc to distinguish between conv3x3s1_depthwise_fp32.cc

* delete printf note in conv3x3s1, test=develop

* delete printf note, test=develop

* delete gem_sdot.h, test=develop

it is coped from __gemm_sdot_meta_.h

* update compute padding, test=develop

* fix padding size, must be 2 or 4. test=develop

* fix format in operators/conv_op.cc, test=develop

* change #if 0 to #if 1, test=develop

* put 2-pad to 4-pad in AttachImpl, test=develop

* fix clang-format error inn tests/math/connv_compute_test, test=develop

* fix x86 test result error, test=develop

* add asymmetric padding test case in liite/tests/math/conv_compute.cc, test=develop

* change paddings type to support dynamically modify, test=develop

* fix x86 build error in connv_compute_test, test=develop

* fix opencl build error, test=develop

* fix oopencl build error, test=develop

* fix  opencl/conv_compute build error, test=develop

* fix  opencl/conv_compute build error, test=develop

* fix format in kernels/opencl/conv_computte_ttest,test=develop

* fix build error, test=develop

fix build error in kernels/x86/conv_compute.h

* fix ccompute shape error in ooperators/conv_op.h, test=develop

* add opencl concat kernell

* fix

* fix

* add model input test

* fix build error

* fix builld error

* add ut in opencl

* add ut

* fix kernel name

* fix kernel namedd

* fix ut

* add concat ut, test=develop

* fix axis compute, test=develop

* add other axis, test=develop

* fix ut. test=develop

* fix format

* delete extra files, test=develop

* fix origin, test=develop

* fix format. test=develop

* fix format2 test=develop

* add leakyrelu and tanh compute

* add init val

* fix leakyrelu and tanh compute error, test=develop

* fix leakyrelu and tanh compute error, test=develop

* delete extra file, test=develop

* delete file

* fix format

* delete extra file, test=develop

* fix format， test=develop

* fix format. test=develop

* add grid sampler

* reset act

* fix conflict and readme, test=develop

* fix ios run error, test=develop

* fix ios run error

* fix ios v8 run error

* fix grid_sampler compute error. test=develop

* fix exp act run error, test=develop

* fix format, test=develop

* fix format， test=develop

* fix redefine error

* fix format, test=develop

* add bilinear interp

* fix formart

* fix build error

* fix pad2d error

* fix format

* fixr

* fix

* fix format. test=develop

* fix format, test=develop

* fix resize error

* fix format. test=develop

* fix format, test=develop

* fix format

* note log(4) << x_image. test=develop

* note x_image printf. test=develop

* fix v7 clang bug. test=develop

* fix format, test=develop

* fix .a build bug, test=develop

* fix resize bug

* fix resize bug

* test=develop

* add cvv ut

* fix clang v7 error

* fix cv errorr, test=develop

* fix conv test bug, test=develop

* fix ut

* fix ut , test=develop

* fix format, test=develop

* change ut, test=develop

* change ut, test=develop

* fix conv ut, test=develop

* fix format, test=develop

* fix resie bug

* fix format, test=develop

* fix compute error

* fix format, test=develop

* fix format, test=develop

* fix memory bug, test=develop

* fix format. test=develop

* 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

* test=develop

* fix build error, test=develop

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

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][OPENCL] fix opencl fc kernel. test=develop

* [LITE][OPENCL] add lws for opencl conv image kernel. test=develop

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

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][OPENCL] fix opencl fc kernel. test=develop

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

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][OPENCL] Fix issue(previous definition in gcc.a) armv7 gcc compile for opencl. test=develop

* 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 resie bug

* fix format, test=develop

* fix memory bug, test=develop

* fix format. test=develop

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

* fix act in conv3x3opt opencl kernel. test=develop

* [LITE][DEMO] fix input arg. test=develop

* fix shutdownlog for std::endl. test=develop