You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<li>[2022-08-18] :fire: PaddleLabel, an intelligent annotation tool has been released in beta. It can annotate data for computer vision tasks such as classification, detection, and segmentation. For more details, please refer to <ahref="./contrib/PaddleLabel/README.md">PaddleLabel</a>. </li>
27
26
<li>[2022-07-20] :fire: PaddleSeg v2.6 is released! More details in <ahref="https://github.com/PaddlePaddle/PaddleSeg/releases">Release Notes</a>.</li>
28
27
<ul>
29
-
<li>Release <a href="./contrib/PP-HumanSeg">PP-HumanSeg v2</a>, an off-the-shelf human segmentation model. It achieves 64.26 FPS on the mobile device, which is 45.5% faster than before. </li>
30
-
<li>Release <a href="./EISeg">EISeg v1.0</a>, the stable-version semi-automatic tool for image, video and 3D slice data annotation. It achieves "Once for All" (training once, and labelling all) performance. </li>
31
-
<li>Release <a href="./configs/pssl">PSSL</a>, a novel pre-training method, including a large dataset that consists of 1.2M+ pseudo semantic segmentation labels corresponding to the whole ImageNet training set. It boosts the performances of various models on all downstream tasks.
32
-
<li>Release <a href="./Matting">PP-Matting</a> source code and the pre-trained models. Also, add five more matting methods in machine learning that allow direct usage without training.</li>
33
-
<li>Release the industrial model series: high-accuracy models, light-weight models, and super light-weight models, to help developers pick up the most suitable one.</li>
28
+
<li>Release <a href="./Matting/">PP-MattingV2</a>, an real-time human matting model with SOTA performance. Compared to previous models, the mean of error is reduced by 17.91%, the inference speed is improved by 44.6% on GPU. </li>
29
+
<li>Release <a href="./contrib/MedicalSeg/">MedicalSegV2</a>, a superior 3D medical image segmentation solution, including an intelligent annotation toolkit called EISeg-Med3D, several state-of-the-art models and an optimized nnUNet-D with high performance.</li>
30
+
<li>Official Release <a href="./configs/rtformer/">RTFormer</a>, an real-time semantic segmentation model. It is proposed by Baidu and accepted by NeurIPS 2022.
34
31
</ul>
35
-
<li>[2022-04-20] PaddleSeg v2.5 released a real-time semantic segmentation model <ahref="./configs/pp_liteseg">PP-LiteSeg</a>, a trimap-free image matting model <ahref="./Matting">PP-Matting</a>, and an easy-to-use toolkit for 3D medical image segmentation <ahref="./contrib/MedicalSeg">MedicalSeg</a>.</li>
36
-
<li>[2022-01-20] We release PaddleSeg v2.4 with EISeg v0.4, and <ahref="./contrib/PP-HumanSeg">PP-HumanSeg</a> including open-sourced dataset <ahref="./contrib/PP-HumanSeg/paper.md#pp-humanseg14k-a-large-scale-teleconferencing-video-dataset">PP-HumanSeg14K</a>. </li>
32
+
<li>[2022-07-20] PaddleSeg v2.6 released an real-time human segmentation SOTA solution <ahref="./contrib/PP-HumanSeg">PP-HumanSegV2</a>, a stable-version semi-automatic segmentation annotation <ahref="./EISeg">EISeg v1.0</a>, a pseudo label pre-training method <ahref="./configs/pssl">PSSL</a> and the source code of <ahref="./Matting">PP-MattingV1</a> </li>
33
+
<li>[2022-04-20] PaddleSeg v2.5 released a real-time semantic segmentation model <ahref="./configs/pp_liteseg">PP-LiteSeg</a>, a trimap-free image matting model <ahref="./Matting">PP-MattingV1</a>, and an easy-to-use solution for 3D medical image segmentation <ahref="./contrib/MedicalSeg">MedicalSegV1</a>.</li>
34
+
<li>[2022-01-20] We release PaddleSeg v2.4 with EISeg v0.4, and <ahref="./contrib/PP-HumanSeg">PP-HumanSegV1</a> including open-sourced dataset <ahref="./contrib/PP-HumanSeg/paper.md#pp-humanseg14k-a-large-scale-teleconferencing-video-dataset">PP-HumanSeg14K</a>. </li>
37
35
38
36
</ul>
39
37
@@ -137,6 +135,10 @@ PaddleSeg is an end-to-end high-efficent development toolkit for image segmentat
-[2022-9]Added 3 cutting-edge models to support whole process deployment applications, including nnformer, TransUnet and nnUnet, allowing you to experience a stronger and more accurate segmentation effect; a new 3D medical image intelligent annotation platform [EISeg-Med3D](../../EISeg/med3d/README_en.md) to quickly and easily achieve accurate 3D medical image annotation.
48
-
-[2022-4]MedicalSeg releases version 0.1, which provides the whole process from data preprocessing in 3D medical image segmentation to training and deployment, including native support for five datasets, and high-precision preprocessing on vertebrae and lungs Train the model.
47
+
-[2022-9]Release MedicalSegV2. It provides 3 cutting-edge models to support whole process deployment applications, including nnformer, TransUnet and nnUnet, allowing you to experience a stronger and more accurate segmentation effect; a new 3D medical image intelligent annotation platform [EISeg-Med3D](../../EISeg/med3d/README_en.md) to quickly and easily achieve accurate 3D medical image annotation.
48
+
-[2022-4]Release MedicalSegV1. It provides the whole process from data preprocessing in 3D medical image segmentation to training and deployment, including native support for five datasets, and high-precision preprocessing on vertebrae and lungs Train the model.
49
49
50
50
51
51
## <imgsrc="../../docs/images/chat.png"width="25"/> Communicate with us
0 commit comments