* Fix exeception when finishing training in detection.
* Fix fluid.Trainer in HiNAS_models.
* Remove coco doc in SSD detection.

* Add CE for face detection.

* add pyreader

* refine cpm and interp_mode

* refine eval and update pyramidbox parameter init

* close mem_opt in pyramidbox

* Refine evaluation code.
* Clean code.

* Speed data processing by multi-threads/multi-process.
* Add profiling scripts.
* Use depthwise transposed conv2d.

* Fix bug in data anchor sampling.
* Add argument for memory optimization.
* Change arguments in detection_output.

* Add data anchor sampling in PyramidBox paper.

* Add head bbox for Pyramid-Box model.

* Fix bug in transform_labels and satisfy_sample_constraint function.

* Add object_coverage constraint & fix bbox_labels data layout bug

* code clean

* Support groups in de-conv and fix bug.

* Clean code.

* Fix model config.

* Some mirror changes in data argumentations.

* Set learning rate by input arguments.

* Support groups in de-conv and fix bug.

* Clean code.

* training code of pyramidbox

* Fix code format.

* load pretrained vgg model

* load pretrained vgg model

* delete irrelevant tools

* delete unused lines

* PyramidBox for face detection.

* Update some hyper parameters.

* Update pyramidbox.py