未验证 提交 a0264403 编写于 作者: H Harryoung 提交者: GitHub

Provide some doc fixes for 3 seg models. (#5675)

上级 adf13887
......@@ -39,4 +39,4 @@ PP-HumanSegV2 | 256x144 | 96.63 | 70.67
## 2. 相关使用说明
1. https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/contrib/PP-HumanSeg
\ No newline at end of file
1. [https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/contrib/PP-HumanSeg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/contrib/PP-HumanSeg)
\ No newline at end of file
......@@ -39,4 +39,4 @@ PP-HumanSegV2 | 256x144 | 96.63 | 70.67
## 2. Reference
Ref: https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/contrib/PP-HumanSeg
Ref: [https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/contrib/PP-HumanSeg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/contrib/PP-HumanSeg)
......@@ -13,7 +13,7 @@
"\n",
"2022年7月,PaddleSeg重磅升级的PP-HumanSegV2人像分割方案,以96.63%的mIoU精度, 63FPS的手机端推理速度,再次刷新开源人像分割算法SOTA指标。相比PP-HumanSegV1方案,推理速度提升87.15%,分割精度提升3.03%,可视化效果更佳。V2方案可与商业收费方案媲美,而且支持零成本、开箱即用!\n",
"\n",
"PP-HumanSeg由飞桨官方出品,是PaddleSeg团队推出的模型和方案。 更多关于PaddleSeg可以点击 https://github.com/PaddlePaddle/PaddleSeg 进行了解。"
"PP-HumanSeg由飞桨官方出品,是PaddleSeg团队推出的模型和方案。 更多关于PaddleSeg可以点击 [https://github.com/PaddlePaddle/PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg) 进行了解。"
]
},
{
......@@ -417,4 +417,3 @@
"nbformat": 4,
"nbformat_minor": 5
}
......@@ -13,7 +13,7 @@
"\n",
"In July 2022, PaddleSeg upgraded PP-HumanSeg to PP-HumanSegV2, providing new portrait segmentation solution which refreshed the SOTA indicator of the open-source portrait segmentation solutions with 96.63% mIoU accuracy and 63FPS mobile inference speed. Compared with the V1 solution, the inference speed is increased by 87.15%, the segmentation accuracy is increased by 3.03%, and the visualization effect is better. The PP-HumanSegV2 is comparable to the commercial solutions!\n",
"\n",
"PP-HumanSeg is officially produced by PaddlePaddle and proposed by PaddleSeg team. More information about PaddleSeg can be found here https://github.com/PaddlePaddle/PaddleSeg."
"PP-HumanSeg is officially produced by PaddlePaddle and proposed by PaddleSeg team. More information about PaddleSeg can be found here [https://github.com/PaddlePaddle/PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg)."
]
},
{
......
......@@ -43,4 +43,4 @@ PP-LiteSeg-B2 | STDC2 | 768x1536 | 78.2 | 77.5 | 102.6|
## 2. 相关使用说明
1. https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/configs/pp_liteseg
1. [https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/configs/pp_liteseg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/configs/pp_liteseg)
......@@ -41,4 +41,4 @@ PP-LiteSeg-B2 | STDC2 | 768x1536 | 78.2 | 77.5 | 102.6|
</div>
## 2. Reference
Ref: https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/configs/pp_liteseg
Ref: [https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/configs/pp_liteseg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.6/configs/pp_liteseg)
......@@ -4,16 +4,16 @@
| 模型名 | 骨干网络 | 训练迭代次数 | 训练输入尺寸 | 预测输入尺寸 | 精度mIoU | 精度mIoU(flip) | 精度mIoU(ms+flip) | 下载链接 |
| --- | --- | --- | ---| --- | --- | --- | --- | --- |
|PP-LiteSeg-T|STDC1|160000|1024x512|1025x512|73.10%|73.89%|-|[config](./pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|1536x768|76.03%|76.74%|-|[config](./pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|2048x1024|77.04%|77.73%|77.46%|[config](./pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|1024x512|75.25%|75.65%|-|[config](./pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|1536x768|78.75%|79.23%|-|[config](./pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|2048x1024|79.04%|79.52%|79.85%|[config](./pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|1025x512|73.10%|73.89%|-|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|1536x768|76.03%|76.74%|-|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|2048x1024|77.04%|77.73%|77.46%|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|1024x512|75.25%|75.65%|-|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|1536x768|78.75%|79.23%|-|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|2048x1024|79.04%|79.52%|79.85%|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k_inference_model.zip)|
## 2 CamVid上语义分割模型
| 模型名 | 骨干网络 | 训练迭代次数 | 训练输入尺寸 | 预测输入尺寸 | 精度mIoU | 精度mIoU(flip) | 精度mIoU(ms+flip) | 下载链接 |
| --- | --- | --- | ---| --- | --- | --- | --- | --- |
|PP-LiteSeg-T|STDC1|10000|960x720|960x720|73.30%|73.89%|73.66%|[config](./pp_liteseg_stdc1_camvid_960x720_10k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/camvid/pp_liteseg_stdc1_camvid_960x720_10k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_camvid_960x720_10k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|10000|960x720|960x720|75.10%|75.85%|75.48%|[config](./pp_liteseg_stdc2_camvid_960x720_10k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/camvid/pp_liteseg_stdc2_camvid_960x720_10k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_camvid_960x720_10k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|10000|960x720|960x720|73.30%|73.89%|73.66%|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc1_camvid_960x720_10k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/camvid/pp_liteseg_stdc1_camvid_960x720_10k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_camvid_960x720_10k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|10000|960x720|960x720|75.10%|75.85%|75.48%|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc2_camvid_960x720_10k.yml)\|[训练模型](https://paddleseg.bj.bcebos.com/dygraph/camvid/pp_liteseg_stdc2_camvid_960x720_10k/model.pdparams)\|[预测模型](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_camvid_960x720_10k_inference_model.zip)|
......@@ -4,16 +4,16 @@
| Model | Backbone | Training Iters | Train Resolution | Test Resolution | mIoU | mIoU (flip) | mIoU (ms+flip) | Links |
| --- | --- | --- | ---| --- | --- | --- | --- | --- |
|PP-LiteSeg-T|STDC1|160000|1024x512|1025x512|73.10%|73.89%|-|[config](./pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|1536x768|76.03%|76.74%|-|[config](./pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|2048x1024|77.04%|77.73%|77.46%|[config](./pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|1024x512|75.25%|75.65%|-|[config](./pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|1536x768|78.75%|79.23%|-|[config](./pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|2048x1024|79.04%|79.52%|79.85%|[config](./pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|1025x512|73.10%|73.89%|-|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale0.5_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|1536x768|76.03%|76.74%|-|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale0.75_160k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|160000|1024x512|2048x1024|77.04%|77.73%|77.46%|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_cityscapes_1024x512_scale1.0_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|1024x512|75.25%|75.65%|-|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale0.5_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|1536x768|78.75%|79.23%|-|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale0.75_160k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|160000|1024x512|2048x1024|79.04%|79.52%|79.85%|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/cityscapes/pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_cityscapes_1024x512_scale1.0_160k_inference_model.zip)|
## 2 Semantic segmentation models on CamVid
| Model | Backbone | Training Iters | Train Resolution | Test Resolution | mIoU | mIoU (flip) | mIoU (ms+flip) | Links |
| --- | --- | --- | ---| --- | --- | --- | --- | --- |
|PP-LiteSeg-T|STDC1|10000|960x720|960x720|73.30%|73.89%|73.66%|[config](./pp_liteseg_stdc1_camvid_960x720_10k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/camvid/pp_liteseg_stdc1_camvid_960x720_10k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_camvid_960x720_10k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|10000|960x720|960x720|75.10%|75.85%|75.48%|[config](./pp_liteseg_stdc2_camvid_960x720_10k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/camvid/pp_liteseg_stdc2_camvid_960x720_10k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_camvid_960x720_10k_inference_model.zip)|
|PP-LiteSeg-T|STDC1|10000|960x720|960x720|73.30%|73.89%|73.66%|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc1_camvid_960x720_10k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/camvid/pp_liteseg_stdc1_camvid_960x720_10k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc1_camvid_960x720_10k_inference_model.zip)|
|PP-LiteSeg-B|STDC2|10000|960x720|960x720|75.10%|75.85%|75.48%|[config](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg//pp_liteseg_stdc2_camvid_960x720_10k.yml)\|[Pretrained_model](https://paddleseg.bj.bcebos.com/dygraph/camvid/pp_liteseg_stdc2_camvid_960x720_10k/model.pdparams)\|[inference_model](https://paddleseg.bj.bcebos.com/inference/pp_liteseg_infer_models/pp_liteseg_stdc2_camvid_960x720_10k_inference_model.zip)|
......@@ -13,7 +13,7 @@
"\n",
"在Cityscapes测试集上使用NVIDIA GTX 1080Ti进行实验,PP-LiteSeg的精度和速度可以达到 72.0% mIoU / 273.6 FPS 以及 77.5% mIoU / 102.6 FPS。与其他模型相比,PP-LiteSeg在精度和速度之间实现了SOTA平衡。\n",
"\n",
"PP-LiteSeg模型由飞桨官方出品,是PaddleSeg团队推出的SOTA模型。 更多关于PaddleSeg可以点击 https://github.com/PaddlePaddle/PaddleSeg 进行了解。"
"PP-LiteSeg模型由飞桨官方出品,是PaddleSeg团队推出的SOTA模型。 更多关于PaddleSeg可以点击 [https://github.com/PaddlePaddle/PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg) 进行了解。"
]
},
{
......@@ -285,4 +285,3 @@
"nbformat": 4,
"nbformat_minor": 5
}
......@@ -13,7 +13,7 @@
"\n",
"On the Cityscapes test set, PP-LiteSeg achieves 72.0% mIoU/273.6 FPS and 77.5% mIoU/102.6 FPS on NVIDIA GTX 1080Ti. PP-LiteSeg achieves a superior tradeoff between accuracy and speed compared to other methods.\n",
"\n",
"PP-LiteSeg model is officially produced by PaddlePaddle and is a SOTA model proposed by PaddleSeg. More information about PaddleSeg can be found here https://github.com/PaddlePaddle/PaddleSeg."
"PP-LiteSeg model is officially produced by PaddlePaddle and is a SOTA model proposed by PaddleSeg. More information about PaddleSeg can be found here [https://github.com/PaddlePaddle/PaddleSeg](https://github.com/PaddlePaddle/PaddleSeg)."
]
},
{
......
......@@ -35,4 +35,4 @@
| ppmatting_hrnet_w18 | PPM-AIM-195 | 31.56|0.0022|31.80|30.13| 24.5 | 91.28 | 28.9 |
## 3. 相关使用说明
1. https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting
1. [https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting)
......@@ -33,4 +33,4 @@
| ppmatting_hrnet_w18 | PPM-AIM-195 | 31.56|0.0022|31.80|30.13| 24.5 | 91.28 | 28.9 |
## 3. Reference
1. https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting
1. [https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting)
......@@ -9,9 +9,9 @@
"\n",
"在众多图像抠图算法中,为了追求精度,往往需要输入trimap作为辅助信息,但这极大限制了算法的使用性。PP-Matting作为一种trimap-free的抠图方法,有效克服了辅助信息带来的弊端,在Composition-1k和Distinctions-646数据集中取得了SOTA的效果。PP-Matting利用语义分支(SCB)提取图片高级语义信息并通过引导流设计(Guidance Flow)逐步引导高分辨率细节分支(HRDB)对过度区域的细节提取,最后通过融合模块实现语义和细节的融合得到最终的alpha matte。\n",
"\n",
"更多细节可参考技术报告:https://arxiv.org/abs/2204.09433 。\n",
"更多细节可参考技术报告:[https://arxiv.org/abs/2204.09433](https://arxiv.org/abs/2204.09433) 。\n",
"\n",
"更多关于PaddleMatting的内容,可以点击 https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting 进行了解。\n",
"更多关于PaddleMatting的内容,可以点击 [https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting) 进行了解。\n",
"\n"
]
},
......@@ -173,20 +173,22 @@
"metadata": {},
"source": [
"## 6. 相关论文以及引用信息\n",
"```\n",
"@article{chen2022pp,\n",
" title={PP-Matting: High-Accuracy Natural Image Matting},\n",
" author={Chen, Guowei and Liu, Yi and Wang, Jian and Peng, Juncai and Hao, Yuying and Chu, Lutao and Tang, Shiyu and Wu, Zewu and Chen, Zeyu and Yu, Zhiliang and others},\n",
" journal={arXiv preprint arXiv:2204.09433},\n",
" year={2022}\n",
"}"
"}\n",
"```"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3.9.13 64-bit",
"language": "python",
"name": "py35-paddle1.2.0"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
......@@ -198,7 +200,12 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.4"
"version": "3.9.13"
},
"vscode": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
}
}
},
"nbformat": 4,
......
......@@ -10,9 +10,9 @@
"\n",
"In many image matting algorithms, in order to pursue precision, trimap is often provided as auxiliary information, but this greatly limits the application of the algorithm. PP-Matting, as a trimap-free image matting method, overcomes the disadvantages of auxiliary information and achieves SOTA performance in Composition-1k and Distinctions-646 datasets. PP-Matting uses Semantic Context Branch (SCB) to extract high-level semantic information of images and gradually guides high-resolution detail branch (HRDB) to extract details in transition area through Guidance Flow. Finally, alpha matte is obtained by fusing semantic map and detail map with fusion module.\n",
"\n",
"More details can be found in the paper: https://arxiv.org/abs/2204.09433.\n",
"More details can be found in the paper: [https://arxiv.org/abs/2204.09433](https://arxiv.org/abs/2204.09433).\n",
"\n",
"More about PaddleMatting,you can click https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting to learn.\n",
"More about PaddleMatting,you can click [https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/Matting) to learn.\n",
"\n"
]
},
......@@ -176,20 +176,22 @@
"metadata": {},
"source": [
"## 6. Related papers and citations\n",
"```\n",
"@article{chen2022pp,\n",
" title={PP-Matting: High-Accuracy Natural Image Matting},\n",
" author={Chen, Guowei and Liu, Yi and Wang, Jian and Peng, Juncai and Hao, Yuying and Chu, Lutao and Tang, Shiyu and Wu, Zewu and Chen, Zeyu and Yu, Zhiliang and others},\n",
" journal={arXiv preprint arXiv:2204.09433},\n",
" year={2022}\n",
"}"
"}\n",
"```"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3.9.13 64-bit",
"language": "python",
"name": "py35-paddle1.2.0"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
......@@ -201,7 +203,12 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.4"
"version": "3.9.13"
},
"vscode": {
"interpreter": {
"hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
}
}
},
"nbformat": 4,
......
Markdown is supported
0% .
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