* allow forwarding for multi scale inputs

* fixed PadBatch not working with multi scale input

* add faster_rcnn_r34_fpn_multiscaletest_1x_coco.yml

* fixed multi scale input checking for batch transforms (PadBatch)

* less scales and faster inference for multi scale test configuration file

* fixed retrieving im_id from multi-scale inputs

* add multi scale prediction boxes merging

* allow multi scale testing for tools/infer.py (actually trainer.predict method)

* add MultiscaleTestResize setting for TestReader

* use BBoxPostProcess.nms parameter for multi scale prediction NMS of CascadeRCNN

* add documentation for multi scale testing

* raise exception if the network architecture is not supported in multi scale test mode

* move documentation file

* add test case for multi scale test

* load pretrained weights from URL

* add image files for testing. use relative path for input images

* update documentation

* use isinstance for sequence type checking. add empty checking for samples sequence

* add sparsercnn

* update sparsercnn

* s2anet fix export and deploy

* remove redundant code

* fix cpp for s2anet deploy

* fix bug of get_categories

* rename poly_to_rbox to poly2rbox

* add some comment for function

* add ttfnet enhance

* add doc

* fix pafnet training

* Add S2ANet model for Oriented Object Detection.

* support not pad gt in rcnn model

* add comment in reader

* add ppyolo r18vd mbv3, yolov3 r50vd

* modify TestReader of ppyolo mbv3 r18vd

* add clip to avoid nan, modify ema to apply ema on bn mean and bn var

* fix code resulting in nan

* add yolov3 r50vd dcn configs

* finish yolo_series and fix some problems

* hide --bias flag and modify docs

* modify --bias and fix deploy/python/infer

* fcos infer

* fcos training

* fix stgraph fcosloss

* fcos doc

* fix dy_fcos

* add comment

* train eval deploy fcos

* remove fcos config, add comment

* fix iter_tic
Co-authored-by: Nnemonameless <nemonameless@qq.com>
Co-authored-by: Ngeorgenemo <nifeng@pku.edu.cn>

Merge dygraph branch into master branch.
Co-authored-by: NFDInSky <48318485+FDInSky@users.noreply.github.com>
Co-authored-by: Nsunxl1988 <47514455+sunxl1988@users.noreply.github.com>
Co-authored-by: Nwangguanzhong <jerrywgz@126.com>
Co-authored-by: Nwangxinxin08 <69842442+wangxinxin08@users.noreply.github.com>
Co-authored-by: Nwanghuancoder <wanghuancoder@163.com>
Co-authored-by: Ncnn <liuhui29@baidu.com>
Co-authored-by: NGuanghua Yu <742925032@qq.com>
Co-authored-by: NKaipeng Deng <dengkaipeng@baidu.com>
Co-authored-by: Nroot <root@bjyz-sys-gpu-kongming0.bjyz.baidu.com>

* update ppyolo_mobilenet_v3 large & small

* add solov2 model

* fix train batch size

* add solov2_r101_vd_fpn_3x

* fix batch size and update modelzoo

* refactor code of solov2

* fix deploy/python

add htc model 

* add yolov4

* fcos initialization

* delete the codes not used

* pre-commit the committed code

* delete the unused function

* modify the capacity in loader from 64 to 16

* split yolov3 loss

* Polish Reader to simplify preprocessing logic.
#  sample_transforms-> make batch -> batch_transforms in Reader.
* Clean some code
* Imporve yolov3_r50vd_dcn_obj365_pretrained_coco 41.4 to 41.8.
* Update all configs.