fix 8-gpus training command for TridentNet (facebookresearch#184)

Summary:
--num_gpus shuold be --num-gpus.
Pull Request resolved: facebookresearch#184

Differential Revision: D18216549

Pulled By: ppwwyyxx

fbshipit-source-id: d5272a55bc892169ad9e77ee4293aec9ce706189

Author: BigBookPlus

projects/TridentNet/README.md

@@ -23,7 +23,7 @@ python /path/to/detectron2/projects/TridentNet/train_net.py --config-file <confi
 For example, to launch end-to-end TridentNet training with ResNet-50 backbone on 8 GPUs,
 one should execute:
 ```bash
-python /path/to/detectron2/projects/TridentNet/train_net.py --config-file configs/tridentnet_fast_R_50_C4_1x.yaml --num_gpus 8
+python /path/to/detectron2/projects/TridentNet/train_net.py --config-file configs/tridentnet_fast_R_50_C4_1x.yaml --num-gpus 8
 ```
 
 ## Evaluation