* Add beam search for dygraph Transformer.
Re-organize dygraph Transformer.

* Add custumed data support for dygraph Transformer.

* Add validation in dygraph Transformer.

* Update notes for multi-gpu for dygraph Transformer.

* Revert "add check version (#3530)"

This reverts commit 2a167ec9.

* Revert "Upgrade API for gnn (#3503)"

This reverts commit 80b01801.

* Revert "upgrade API for DIN (#3499)"

This reverts commit 734812c3.

* 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 version checking for DIN and SR-GNN.

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

* unify reader to dataloader

* add check_version

* fix some configs

* fix doc

* change PyReader to from_generator

* fluid.layers.data->fluid.data

* fix_bug

* user new save load in all dygraph modell; test=develop

* change load_dict to set_dict; test=develop