settins -> settings

2. Added FSAF model zoo

Co-authored-by: wangxinjiang <wangxinjiang@sensetime.com>

A major new release of v2.0

* rename anchor_heads to dense_heads

* update docs

* update docs

* update doc with code block

* add python path in scripts

* Make python path work

* Shorter path

* Add docs

* Change dist scripts

* Change slurm example

* add print_config.py tool

* update docs

* update dockerfile

* typo fix

* add compare table fix model_zoo.md

* fix some typos

* minor add

* minor update

* add link for mmdet

* minor update

* fix the docs

* add docs for image demo

* add macOS in supported systems

* add mmcv into requirements of readthedocs

* add v2.0 changelog

* minor updates

* add speedup percentage

* update changelog

* update the release date

* add api doc

* update mock modules and fix requirements

* fix autodoc modules

* remove tmp file

* add release version in docs/conf.py

* fix docstring styles

V2.0

* move shared_heads, mask_heads, bbox_heads under roi_heads

* move roi_extractor

* remove widlcard import

* remove ... import

* Add score_thr parameter to test

* Add info about score_thr in docs

* Rename score_thr to show_score_thr

* Fix show-score-thr name in getting_started.md

* fixed cityscapes pretrain model path

* fixed empirical attention stages

* starting to merge fsaf

* changed configs

* changed bbox_coder

* get_targets fun in AnchorHead class is modified to enable additional returns from _get_target_single

* effective area assigner and tblr bbox_coder are implemented

* added fsaf_head and config

* added more fsaf configs

* fixed the nan bbox_loss by clamping bbox_pred with min=1e-4

* fixed the nan bbox_loss by clamping bbox_pred with min=1e-4

* changed config

* formatter

* changed docstring

* Added ignored pixel-class pair for FSAF

* More elegant assignment for overlapping objects

* more documents in effective area assigner

* fixed a bug in object overlay

* Added no gt_bboxes case and pytest for assigner

* Added no gt_bboxes case and pytest for assigner

* changed default config

* fixed small bugs in FSAF head doc example

* resolved pr review comments.
1. Formats of comments and docstrings are modified
2. Obsolete arguments are removed from FSAFHead
3. AssignResults class is revised to be more compatible with old version

* Added more comments to FSAFHead

* resolved pr review comments

* resolved pr review comments
1. More flexible CenterRegionAssigner bbox priority
2. More flexible tblr_coder by adding normalize_by_wh flag
3. README modifications with model link
4. More docstrings and comments
5. Reformatted
6. Change of default normalizer in TBLRBBoxCoder from 1.0 to 4.0

* Corrected FSAF model path in readme

* Fixed the bug of bbox weights in fsaf head

* trying to add fsafhead test

* Added FSAFHead test and supported zero gt in FSAFHead

Co-authored-by: wangxinjiang <wangxinjiang@sensetime.com>

* Add gradient clip back in cfgs

* Reformat cfg

Co-authored-by: zww <zhangwenwei@sensetime.com>

* Enrich dataset tutorial

* Add an example

* Modify the demo

* Change demo format

* change logic

* Reformat code in tutorial

* fixed webcam demo

* fixed show=True

* add warning when show=False and out_file=None

* add docs

* reorg tutorials and a minor fix

* add docs on adding new necks

* fix bbox_loss in fovea_head.py when num_pos=0

* Remove PIL from .isort.cfg

* Make loss_bbox scalar in fovea_head.py when num_pos==0

* Sum based reduction for loss_bbox in fovea_head

* reverting to scalar implementation

* migrate to mmcv.cnn.bricks

* remove conv_module, scale, upsample

* update mmdet version and mmcv requirement

* fixed fsaf warning

* Add fsaf into regression benchmark

* Cover more cases in unittest & regression benchmark

* Minor fix

* rm nas_fpn from test_pipeline

* avoid duplicated cfgs

* add configs for all models

* fix some configs

* Add benchmark models

* update some benchmarks

* Fix retina config

* add more benchmarks

* update MODEL_ZOO.md

* fix cascade mask num_class bug

* change caffe pretrained url

* fix paramwise_cfg bug

* fix paramwise cfg

* restrict minimum h and w in crop_and_resize

* add grad clip for fcos

* add grad clip for ga retinanet

* fix grad clip

* fix img norm

* fix rpn loss bbox

* fix rpn proposal num

* fix url

* clean

* update comparison

* minor update

* add grad clip for guided anchoring

* fix some typos

* add inference time details

* clean

Co-authored-by: ZwwWayne <wayne.zw@outlook.com>

* Add tutorials for V2.0

* Add details for dataset tutorial

* add tutorials in index.rst

* Add tutorials for concat data

* Modify documents

* More contents

* starting to merge fsaf

* changed configs

* changed bbox_coder

* get_targets fun in AnchorHead class is modified to enable additional returns from _get_target_single

* effective area assigner and tblr bbox_coder are implemented

* added fsaf_head and config

* added more fsaf configs

* fixed the nan bbox_loss by clamping bbox_pred with min=1e-4

* fixed the nan bbox_loss by clamping bbox_pred with min=1e-4

* changed config

* formatter

* changed docstring

* Added ignored pixel-class pair for FSAF

* More elegant assignment for overlapping objects

* more documents in effective area assigner

* fixed a bug in object overlay

* Added no gt_bboxes case and pytest for assigner

* Added no gt_bboxes case and pytest for assigner

* changed default config

* fixed small bugs in FSAF head doc example

* resolved pr review comments.
1. Formats of comments and docstrings are modified
2. Obsolete arguments are removed from FSAFHead
3. AssignResults class is revised to be more compatible with old version

* Added more comments to FSAFHead

* resolved pr review comments

* resolved pr review comments
1. More flexible CenterRegionAssigner bbox priority
2. More flexible tblr_coder by adding normalize_by_wh flag
3. README modifications with model link
4. More docstrings and comments
5. Reformatted
6. Change of default normalizer in TBLRBBoxCoder from 1.0 to 4.0

* Corrected FSAF model path in readme

* Fixed the bug of bbox weights in fsaf head

Co-authored-by: wangxinjiang <wangxinjiang@sensetime.com>

* Pass momentum_config to register_training_hooks

* Bump mmcv version

* Explicit default