Update README.md

README.md

@@ -62,7 +62,6 @@ DTK驱动：dtk24.04.1
 python：python3.10
 torch: 2.1.0
 torchvision: 0.16.0
-
 ```
 `Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`
 
@@ -128,22 +127,20 @@ python inference.py --image-dir ./images --model-config configs/salience_detr/sa
 
 Evaluation/Test:
 
-```
 <!--
 # CUDA_VISIBLE_DEVICES=<gpu_ids> accelerate launch test.py --coco-path /path/to/coco --model-config /path/to/model.py --checkpoint /path/to/checkpoint.pth
 -->
-
+```
 HIP_VISIBLE_DEVICES=0 accelerate launch test.py --coco-path ./data/coco --model-config configs/salience_detr/salience_detr_resnet50_800_1333.py --checkpoint checkpoint/salience_detr_resnet50_800_1333_coco_2x.pth
 
 ```
 
 
 ### 多卡推理
-
-```
 <!--
 CUDA_VISIBLE_DEVICES=<gpu_ids> accelerate launch test.py --coco-path /path/to/coco --model-config /path/to/model.py --checkpoint /path/to/checkpoint.pth
 -->
+```
 HIP_VISIBLE_DEVICES=0,1,2,3 accelerate launch test.py --coco-path ./data/coco --model-config configs/salience_detr/salience_detr_resnet50_800_1333.py --checkpoint checkpoint/salience_detr_resnet50_800_1333_coco_2x.pth
 ```
 注：如遇到端口被占用的情况，需要在launch后面添加参数--main_process_port用来指定端口