add README.md for GN (#494)

* make pixel indexes 0-based for bounding box in pascal voc dataset

* replacing all instances of torch.distributed.deprecated with torch.distributed

* replacing all instances of torch.distributed.deprecated with torch.distributed

* add GroupNorm

* add GroupNorm -- sort out yaml files

* use torch.nn.GroupNorm instead, replace 'use_gn' with 'conv_block' and use 'BaseStem'&'Bottleneck' to simply codes

* modification on 'group_norm' and 'conv_with_kaiming_uniform' function

* modification on yaml files in configs/gn_baselines/ and reduce the amount of indentation and code duplication

* use 'kaiming_uniform' to initialize resnet, disable gn after fc layer, and add dilation into ResNetHead

* agnostic-regression for bbox

* please set 'STRIDE_IN_1X1' to be 'False' when backbone use GN

* add README.md for GN

configs/gn_baselines/README.md

+### Group Normalization
+1 [Group Normalization](https://arxiv.org/abs/1803.08494)  
+2 [Rethinking ImageNet Pre-training](https://arxiv.org/abs/1811.08883)  
+3 [official code](https://github.com/facebookresearch/Detectron/blob/master/projects/GN/README.md)  
+
+
+### Performance
+|      case                  |    Type      |  lr schd  |  im/gpu | bbox AP | mask AP |
+|----------------------------|:------------:|:---------:|:-------:|:-------:|:-------:|
+|   R-50-FPN, GN (paper)     | finetune     |    2x     |   2     |   40.3  |  35.7   |
+|   R-50-FPN, GN (implement) | finetune     |    2x     |   2     |   40.2  |  36.0   |
+|   R-50-FPN, GN (paper)     | from scratch |    3x     |   2     |   39.5  |  35.2   |
+|   R-50-FPN, GN (implement) | from scratch |    3x     |   2     |   38.9  |  35.1   |