Add commands used to train `fcn_resnet50` and `deeplabv3_resnet50` (#2091)

references/segmentation/README.md

@@ -6,11 +6,21 @@ training and evaluation scripts to quickly bootstrap research.
 
 All models have been trained on 8x V100 GPUs.
 
+## fcn_resnet50
+```
+python -m torch.distributed.launch --nproc_per_node=8 --use_env train.py --lr 0.02 --dataset coco -b 4 --model fcn_resnet50 --aux-loss
+```
+
 ## fcn_resnet101
 ```
 python -m torch.distributed.launch --nproc_per_node=8 --use_env train.py --lr 0.02 --dataset coco -b 4 --model fcn_resnet101 --aux-loss
 ```
 
+## deeplabv3_resnet50
+```
+python -m torch.distributed.launch --nproc_per_node=8 --use_env train.py --lr 0.02 --dataset coco -b 4 --model deeplabv3_resnet50 --aux-loss
+```
+
 ## deeplabv3_resnet101
 ```
 python -m torch.distributed.launch --nproc_per_node=8 --use_env train.py --lr 0.02 --dataset coco -b 4 --model deeplabv3_resnet101 --aux-loss