test=develop

* CUDA kernel for density_prior_box_op.
* Support flatten to 2D.

* Modify some infer-shape in compile-time.

Density prior box operator for image detection model.

test=develop

avoid the default one that usually overwrites manually set ones

test=develop

test=develop

* Add roi perspective transform.

* Add roi_perspective_transform_op.

* Fix code style.

* Add python api and fix doc.

* Fix API.spec

* Fix python api.

* Fix API.spec

* Move src to detection.

* Enhence generate_proposal_labels_op
* Fix bug in generate_proposals_op
* Refine rpn_target_assign_op.
* by Bu Xingyuan, Wang Guanzhong and Dang Qingqing

* Fix bug in generate_proposals_op.
* Fix data type for RoIs.
* Refine and fix rpn_target_assign_op.
* Add the missing file bbox_util.h
* Rename BoxEncoder to BoxToDelta

* Add unit test for rpn_target_assign API.

* Add generate_proposal_labels for Faster-RCNN.

* Add proposals generation operator for Faster-RCNN.

Add flatten op interface and enhance APIs about detection to support variable-length image. (#12422)

* add flatten api&enhance detection api

* unify shape_op data type

* update API.spec

* api clean

* update API.spec

* Add flag to set prior_box output order.

* Add region proposal network (RPN) target assign operator and Python API for Faster-RCNN.

* Add anchor generator operator for Faster-RCNN.
* Add unittest testing.
* Add Python API.