* [metric learning] fix windows download dataset

* fix_infer_bug_release_some_model

* remove actual_shape

* add fpn fix

* fix spade

* update SPADE

* update spade

* update infer

* update infer

* refine doc for transfer learning

* refine yolov3/rcnn/ssd dataset download

* refine docs

* add face doc
* update face detection readme and add demo jpg

* refine download sh to py

* update QUICK_STARTED

* Add C++ inference solution.
* Correct the link.

* Error out if fp16 is enabled and affine channel is used

* Add more documentation on mixed precision training

* add aistudio link in README

* add multi-scale test

* add modes and documents for vehicle and pedestrian detection

* remove needless output images

* add class names

* add Configure for training

* fix table in READ.md

* compress the images in the demo/output

* change the score_threshold for vehicle inference

* change Yolo v3 to YOLOv3

This reverts commit 0be3697c.

* add class aware sampling strategy
* remove redundancy code

This reverts commit 36a2e65b.

* Revert "change PyReader to from_generator (#3490)"

This reverts commit d331b799.

* Update data_reader.py

* Update data_reader.py

* Update utility.py

This reverts commit 04bfe0a8.

This reverts commit b591cc13.

* refine assert info in roidb_source.py

* refine image_dir assert

* fix fluid.data and fluid.io.DataLoader

* add logger in utils/utility.py

* Add face detection configs and main code.
* Integration multi-scale evaluation.