* define data pipelines

* update two config files

* minor fix for config files

* allow img_scale to be optional and update config

* add some docstrings

* add extra aug to transform

* bug fix for mask resizing

* fix cropping

* add faster rcnn example

* fix imports

* fix robustness testing

* add img_norm_cfg to img_meta

* fix the inference api with the new data pipeline

* fix proposal loading

* delete args of DefaultFormatBundle

* add more configs

* update configs

* bug fix

* add a brief doc

* update gt_labels in RandomCrop

* fix key error for new apis

* bug fix for masks of crowd bboxes

* add argument data_root

* minor fix

* update new hrnet configs

* update docs

* rename MultiscaleFlipAug to MultiScaleFlipAug

* add __repr__ for all transforms

* move DATA_PIPELINE.md to docs/

* fix image url

* Inference API support video

* Using mmcv.VideoReader to read video

* modify

* Reformat use yapf 0.27.0

* Add yapf style file

* update the high-level inference api

* save classes in meta data and use it for visualization

* Update README.md

* Update inference.py

* Update README.md

* Update inference.py

Added mask visualization part for inferring.

* Update README.md

* Update inference.py

* Update inference.py

convert all tabs to spaces

* Update inference.py

* Update inference.py

fix inference bug, the default keep_ratio is True...But SSD should be false

* Update inference.py

format correct

* Update inference.py

A more stable way

* Update inference.py

* Update inference.py