add name bn

pretrained_model/download_model.py

@@ -57,7 +57,7 @@ model_urls = {
     "https://paddleseg.bj.bcebos.com/models/unet_coco_v3.tgz",
     "icnet_bn_cityscapes":
     "https://paddleseg.bj.bcebos.com/models/icnet_cityscapes.tar.gz",
-    "pspnet50_cityscapes":
+    "pspnet50_bn_cityscapes":
     "https://paddleseg.bj.bcebos.com/models/pspnet50_cityscapes.tgz"
 }
 

turtorial/finetune_pspnet.md

@@ -21,7 +21,7 @@ python dataset/download_pet.py
 接着下载对应的预训练模型
 
 ```shell
-python pretrained_model/download_model.py pspnet50_cityscapes
+python pretrained_model/download_model.py pspnet50_bn_cityscapes
 ```
 
 ## 三. 准备配置
@@ -117,5 +117,5 @@ python pdseg/eval.py --use_gpu --cfg ./configs/test_pet.yaml
 
 |预训练模型名称|BackBone|Norm|数据集|配置|
 |-|-|-|-|-|
-|pspnet50_cityscapes|ResNet50|bn|Cityscapes|MODEL.MODEL_NAME: pspnet <br> MODEL.DEFAULT_NORM_TYPE: bn <br> MODEL.PSPNET.LAYERS: 50|
-|pspnet101_cityscapes|ResNet101|bn|Cityscapes|MODEL.MODEL_NAME: pspnet <br> MODEL.DEFAULT_NORM_TYPE: bn <br> MODEL.PSPNET.LAYERS: 101|
+|pspnet50_bn_cityscapes|ResNet50|bn|Cityscapes|MODEL.MODEL_NAME: pspnet <br> MODEL.DEFAULT_NORM_TYPE: bn <br> MODEL.PSPNET.LAYERS: 50|
+|pspnet101_bn_cityscapes|ResNet101|bn|Cityscapes|MODEL.MODEL_NAME: pspnet <br> MODEL.DEFAULT_NORM_TYPE: bn <br> MODEL.PSPNET.LAYERS: 101|