do not enable MKL-DNN twice

Add ifdef guard for MKL-DNN placement pass

fix roi pool register

Fix jit exp

After the MKL-DNN placement pass there is no need to enable MKL-DNN
in operators via executor

test=develop

* add detect and end2end code

* update the scale for coodinates restore

* fix merge bug with dev.

* fix merge bug with dev.

* test=develop

* fix code style test=develop

* fix code style test=develop

* test=develop

* test=develop

* test=develop

update readme.md

* add MKL-DNN placement pass

This patch also refactors conv+bn (includes changes from PR
https://github.com/PaddlePaddle/Paddle/pull/13926)
updated to use the mkldnn-placement-pass.

test=develop

* remove redundant pass list

* add comment on the default first pass

* fix test for conv+relu mkldnn fuse

test=develop

set default timeout to avoiding blocking CI

* fix conv doc
test=develop

* fix seq_conv doc
test=develop

* fix simple_img_conv_pool
test=develop

* update API.spec

* update parameter doc
test=develop

* follow comment
test=develop

* fix other layer
test=develop

* fix lstm bias_attr doc
test=develop

Added comment with request for enhancement

test=develop

test=develop

refine mkldnn test in analyzer_tests

Add layer_norm doc to illustrate param_attr and bias_attr

mute api_impl ut ... 

test=develop

test=develop

test=develop

Fix Mac problem: inference model not found

test=develop

This adds a `TODO` comment according to https://github.com/PaddlePaddle/Paddle/issues/13550#issuecomment-430133585

test=develop

Add grpc error context

test=develop

* Add affine channel op.
* Update code and add Python API.
test=develop
* Update API.spec
test=develop

test=develop

fix warning and mac compile

test=develop

test=develop

update readme.md

Clean inference lib

Add rpc timeline