Skip to content

P
PaddleSeg

PaddlePaddle / PaddleSeg

通知 285
Star 8
Fork 1
P
PaddleSeg
提交 12017afd 编写于 作者: C chenguowei01
浏览文件
操作

add resnet_vd backbone

上级 1e810160
隐藏空白更改
内联 并排
Showing with 9 addition and 1 deletion
docs/model_zoo.md
浏览文件 @ 12017afd
......@@ -37,6 +37,7 @@ PaddleSeg对所有内置的分割模型都提供了公开数据集下的预训
|---|---|---|---|
| ResNet50（适配PSPNet） | ImageNet | [resnet50_v2_pspnet](https://paddleseg.bj.bcebos.com/resnet50_v2_pspnet.tgz)| -- |
| ResNet101（适配PSPNet） | ImageNet | [resnet101_v2_pspnet](https://paddleseg.bj.bcebos.com/resnet101_v2_pspnet.tgz)| -- |
| ResNet50_vd | ImageNet | [ResNet50_vd_ssld_pretrained.tgz](https://paddleseg.bj.bcebos.com/models/ResNet50_vd_ssld_pretrained.tgz) | 83.0%/96.4% |
## COCO预训练模型
......@@ -58,7 +59,8 @@ train数据集合为Cityscapes训练集合，测试为Cityscapes的验证集合
|---|---|---|---|---|---|
| DeepLabv3+/MobileNetv2/bn | Cityscapes |[mobilenet_cityscapes.tgz](https://paddleseg.bj.bcebos.com/models/mobilenet_cityscapes.tgz) |16|false| 0.698|
| DeepLabv3+/Xception65/gn | Cityscapes |[deeplabv3p_xception65_gn_cityscapes.tgz](https://paddleseg.bj.bcebos.com/models/deeplabv3p_xception65_cityscapes.tgz) |16|false| 0.7824 |
| DeepLabv3+/Xception65/bn | Cityscapes |[deeplabv3p_xception65_bn_cityscapes_.tgz](https://paddleseg.bj.bcebos.com/models/xception65_bn_cityscapes.tgz) | 16 | false | 0.7930 |
| DeepLabv3+/Xception65/bn | Cityscapes |[deeplabv3p_xception65_bn_cityscapes.tgz](https://paddleseg.bj.bcebos.com/models/xception65_bn_cityscapes.tgz) | 16 | false | 0.7930 |
| DeepLabv3+/ResNet50_vd/bn | Cityscapes |[deeplabv3p_resnet50_vd_cityscapes.tgz](https://paddleseg.bj.bcebos.com/models/deeplabv3p_resnet50_vd_cityscapes.tgz) | 16 | false | 0.8006 |
| ICNet/bn | Cityscapes |[icnet_cityscapes.tgz](https://paddleseg.bj.bcebos.com/models/icnet_cityscapes.tar.gz) |16|false| 0.6831 |
| PSPNet/bn | Cityscapes |[pspnet50_cityscapes.tgz](https://paddleseg.bj.bcebos.com/models/pspnet50_cityscapes.tgz) |16|false| 0.7013 |
| PSPNet/bn | Cityscapes |[pspnet101_cityscapes.tgz](https://paddleseg.bj.bcebos.com/models/pspnet101_cityscapes.tgz) |16|false| 0.7734 |
......
pretrained_model/download_model.py
浏览文件 @ 12017afd
......@@ -42,6 +42,8 @@ model_urls = {
"https://paddleseg.bj.bcebos.com/models/Xception41_pretrained.tgz",
"xception65_imagenet":
"https://paddleseg.bj.bcebos.com/models/Xception65_pretrained.tgz",
"resnet50_vd_imagenet":
"https://paddleseg.bj.bcebos.com/models/ResNet50_vd_ssld_pretrained.tgz",
"hrnet_w18_bn_imagenet":
"https://paddleseg.bj.bcebos.com/models/hrnet_w18_imagenet.tar",
"hrnet_w30_bn_imagenet":
......@@ -76,6 +78,8 @@ model_urls = {
"https://paddleseg.bj.bcebos.com/models/deeplabv3p_xception65_cityscapes.tgz",
"deeplabv3p_xception65_bn_cityscapes":
"https://paddleseg.bj.bcebos.com/models/xception65_bn_cityscapes.tgz",
"deeplabv3p_resnet50_vd_cityscapes":
"https://paddleseg.bj.bcebos.com/models/deeplabv3p_resnet50_vd_cityscapes.tgz",
"unet_bn_coco":
"https://paddleseg.bj.bcebos.com/models/unet_coco_v3.tgz",
"icnet_bn_cityscapes":
......
turtorial/finetune_deeplabv3plus.md
浏览文件 @ 12017afd
......@@ -145,8 +145,10 @@ PaddleSeg在AI Studio平台上提供了在线体验的DeepLabv3+图像分割教
|mobilenetv2-0-25_bn_imagenet|MobileNetV2|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenetv2 <br> MODEL.DEEPLAB.DEPTH_MULTIPLIER: 0.25 <br> MODEL.DEFAULT_NORM_TYPE: bn|
|xception41_imagenet|Xception41|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_41 <br> MODEL.DEFAULT_NORM_TYPE: bn|
|xception65_imagenet|Xception65|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn|
|ResNet50_vd_ssld_pretrained|ResNet50_vd|bn|ImageNet|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: resnet50_vd <br> MODEL.DEFAULT_NORM_TYPE: bn|
|deeplabv3p_mobilenetv2-1-0_bn_coco|MobileNetV2|bn|COCO|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenetv2 <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**|Xception65|bn|COCO|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn |
|deeplabv3p_mobilenetv2-1-0_bn_cityscapes|MobileNetV2|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: mobilenetv2 <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|Xception65|gn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: gn|
|deeplabv3p_xception65_bn_cityscapes|Xception65|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: xception_65 <br> MODEL.DEFAULT_NORM_TYPE: bn|
|deeplabv3p_resnet50_vd_cityscapes|resnet50_vd|bn|Cityscapes|MODEL.MODEL_NAME: deeplabv3p <br> MODEL.DEEPLAB.BACKBONE: resnet50_vd <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