update model url and ms training in README.md (#677)

configs/fcos/README.md

@@ -13,13 +13,13 @@
 
 ## Results and Models
 
-| Backbone  | Style   | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
-|:---------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:|
-| R-50-FPN  | caffe   | 1x      | 6.9      | 0.396               | 13.6           | 36.7   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r50_fpn_1x-9f253a93.pth) |
-| R-50-FPN  | caffe   | 2x      | -        | -                   | -              | 38.7   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r50_fpn_2x-f7329d80.pth) |
-| R-101-FPN | caffe   | 1x      | 10.4     | 0.558               | 11.6           | 39.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r101_fpn_1x-e4889733.pth) |
-| R-101-FPN | caffe   | 2x      | -        | -                   | -              | 40.8   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r101_fpn_2x-42e6f62d.pth) |
-| X-101-64x4d-FPN | caffe   |2x | 9.7      | 0.892               | 7.0            | 42.8   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_x101_64x4d_fpn_2x-a36c0872.pth) |
+| Backbone  | Style   | Multi-scale training | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
+|:---------:|:-------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:|
+| R-50-FPN  | caffe   | N       | 1x      | 6.9      | 0.396               | 13.6           | 36.7   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r50_caffe_fpn_gn_1x_4gpu_20190516-9f253a93.pth) |
+| R-50-FPN  | caffe   | Y       | 2x      | -        | -                   | -              | 38.7   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_r50_caffe_fpn_gn_2x_4gpu_20190516-f7329d80.pth) |
+| R-101-FPN | caffe   | N       | 1x      | 10.4     | 0.558               | 11.6           | 39.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r101_caffe_fpn_gn_1x_4gpu_20190516-e4889733.pth) |
+| R-101-FPN | caffe   | Y       | 2x      | -        | -                   | -              | 40.8   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu_20190516-42e6f62d.pth) |
+| X-101-64x4d-FPN | caffe | Y   |2x       | 9.7      | 0.892               | 7.0            | 42.8   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x_20190516-a36c0872.pth) |
 
 **Notes:**
 - To be consistent with the author's implementation, we use 4 GPUs with 4 images/GPU for R-50 and R-101 models, and 8 GPUs with 2 image/GPU for X-101 models.