* speedup split_op
test=develop

* speedup split_op
test=develop

* rename ConcatGrad to Split

* refine concat and split
test=develop

* fix compile error

handle var type inference

test=develop

avoid the default one that usually overwrites manually set ones

test=develop

core.so do not link libpython test=develop

Refine generate proposals op

Add rpc profiler flags

Fix test_parallel_executor_mnist.py randomly hang.

MKLDNN conv+elementwise_add fusion for residual connections in Resnet

Fea/fusion seqconv eltadd relu

test=develop

test=develop

Add RoI align operator.

test=develop

MKLDNN conv + elementwise_add fusion: UT for missing bias added. UTs refactored. Some minor changes in the pass

test=develop

test=develop

test=develop

test=develop

test=develop

macro used.

test=develop

MKLDNN conv + elementwise_add fusion: skip connection attribute renamed. Comments about patterns added.

test=develop

MKLDNN conv + elementwise_add fusion: Fix transpiler integration to predict skip connection input of eltwise_add

test=develop

MKLDNN conv + elementwise_add fusion: Fix output_data to point to the right tensor, also fix transpiler integration

MKLDNN conv + elementwise_add fusion: some refactoring: consts, function calls instead of constant values