Skip to content

P
PaddleSeg

PaddlePaddle / PaddleSeg

通知 285
Star 8
Fork 1
P
PaddleSeg
未验证 提交 dd1f9116 编写于 作者: W wuyefeilin 提交者： GitHub
浏览文件
操作

Update finetune_deeplabv3plus.md 

模型下载的更改
上级 c632a4c2
隐藏空白更改
内联 并排
Showing with 4 addition and 4 deletion
turtorial/finetune_deeplabv3plus.md
浏览文件 @ dd1f9116
...@@ -21,7 +21,7 @@ python dataset/download_pet.py ...@@ -21,7 +21,7 @@ python dataset/download_pet.py
接着下载对应的预训练模型 接着下载对应的预训练模型
```shell ```shell
python pretrained_model/download_model.py deeplabv3p_xception65_bn_cityscapes python pretrained_model/download_model.py deeplabv3p_xception65_bn_coco
``` ```
## 三. 准备配置 ## 三. 准备配置
...@@ -47,7 +47,7 @@ python pretrained_model/download_model.py deeplabv3p_xception65_bn_cityscapes ...@@ -47,7 +47,7 @@ python pretrained_model/download_model.py deeplabv3p_xception65_bn_cityscapes
数据集的配置和数据路径有关，在本教程中，数据存放在`dataset/mini_pet`中 数据集的配置和数据路径有关，在本教程中，数据存放在`dataset/mini_pet`中
其他配置则根据数据集和机器环境的情况进行调节，最终我们保存一个如下内容的yaml配置文件，存放路径为`configs/test_deeplabv3p_pet.yaml` 其他配置则根据数据集和机器环境的情况进行调节，最终我们保存一个如下内容的yaml配置文件，存放路径为<font color="#dd0000">configs/test_deeplabv3p_pet.yaml</font><br />
```yaml ```yaml
# 数据集配置 # 数据集配置
...@@ -123,7 +123,7 @@ python pdseg/eval.py --use_gpu --cfg ./configs/test_deeplabv3p_pet.yaml ...@@ -123,7 +123,7 @@ python pdseg/eval.py --use_gpu --cfg ./configs/test_deeplabv3p_pet.yaml
|xception41_imagenet|-|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_41 <br> MODEL.DEFAULT_NORM_TYPE: bn| |xception41_imagenet|-|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_41 <br> MODEL.DEFAULT_NORM_TYPE: bn|
|xception65_imagenet|-|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn| |xception65_imagenet|-|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn|
|deeplabv3p_mobilenetv2-1-0_bn_coco|MobileNet V2|bn|COCO|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenet <br> MODEL.DEEPLAB.DEPTH_MULTIPLIER: 1.0 <br> MODEL.DEEPLAB.ENCODER_WITH_ASPP: False <br> MODEL.DEEPLAB.ENABLE_DECODER: False <br> MODEL.DEFAULT_NORM_TYPE: bn| |deeplabv3p_mobilenetv2-1-0_bn_coco|MobileNet V2|bn|COCO|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenet <br> MODEL.DEEPLAB.DEPTH_MULTIPLIER: 1.0 <br> MODEL.DEEPLAB.ENCODER_WITH_ASPP: False <br> MODEL.DEEPLAB.ENABLE_DECODER: False <br> MODEL.DEFAULT_NORM_TYPE: bn|
|deeplabv3p_xception65_bn_coco|Xception|bn|COCO|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn | |**deeplabv3p_xception65_bn_coco**|Xception|bn|COCO|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn |
|deeplabv3p_mobilenetv2-1-0_bn_cityscapes|MobileNet V2|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenet <br> MODEL.DEEPLAB.DEPTH_MULTIPLIER: 1.0 <br> MODEL.DEEPLAB.ENCODER_WITH_ASPP: False <br> MODEL.DEEPLAB.ENABLE_DECODER: False <br> MODEL.DEFAULT_NORM_TYPE: bn| |deeplabv3p_mobilenetv2-1-0_bn_cityscapes|MobileNet V2|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenet <br> MODEL.DEEPLAB.DEPTH_MULTIPLIER: 1.0 <br> MODEL.DEEPLAB.ENCODER_WITH_ASPP: False <br> MODEL.DEEPLAB.ENABLE_DECODER: False <br> MODEL.DEFAULT_NORM_TYPE: bn|
|deeplabv3p_xception65_gn_cityscapes|Xception|gn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: gn| |deeplabv3p_xception65_gn_cityscapes|Xception|gn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: gn|
|**deeplabv3p_xception65_bn_cityscapes**|Xception|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn| |deeplabv3p_xception65_bn_cityscapes|Xception|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn|
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或