Update release note

PaddlePaddle · Feb 26, 2021 · 8119f0d · 8119f0d
1 parent f917936
commit 8119f0d
Show file tree

Hide file tree

Showing 2 changed files with 29 additions and 0 deletions.
diff --git a/docs/release_notes.md b/docs/release_notes.md
@@ -2,6 +2,21 @@ English | [简体中文](release_notes_cn.md)
 
 ## Release Notes
 
+* 2020.02.26
+
+  **`v2.0`**
+  * We newly released version 2.0 which has been fully upgraded to dynamic graphics. It supports more than 20 segmentation models, 4 backbone networks, , 5 datasets and 7 losses:
+    * Segmentation models: ANN, BiSeNetV2, DANet, DeeplabV3, DeeplabV3+, FCN, FastSCNN, Gated-scnn, GCNet, OCRNet, PSPNet, UNet, and U^2Net
+    * Backbone networks: ResNet, HRNet, MobileNetV3, and Xception
+    * Datasets: Cityscapes, ADE20K, Pascal VOC, Pascal Context, COCO Stuff
+    * Losses: CrossEntropy Loss、BootstrappedCrossEntropy Loss、Dice Loss、BCE Loss、OhemCrossEntropyLoss、RelaxBoundaryLoss、OhemEdgeAttentionLoss
+  * We provide more than 50 high quality pre-trained models based on Cityscapes and Pascal Voc datasets.
+  * The new version support multi-card GPU parallel evaluation for more efficient metrics calculation.  It also support multiple evaluation methods such as multi-scale evaluation/flip evaluation/sliding window evaluation.
+  * XPU model training including DeepLabv3, HRNet, UNet, is available now.
+  * We open source  a semantic segmentation model based on the Hierarchical Multi-Scale Attention structure, and it reached 87% mIoU on the Cityscapes validation set.
+  * The dynamic graph mode supports model compression functions such as online quantification and pruning.
+  * The dynamic graph mode supports model export for high-performance deployment.
+
 * 2020.12.18
 
   **`v2.0.0-rc`**

diff --git a/docs/release_notes_cn.md b/docs/release_notes_cn.md
@@ -1,6 +1,20 @@
 简体中文 | [English](release_notes.md)
 
 ## Release Notes
+* 2020.02.26
+
+  **`v2.0`**
+  * 全新发布2.0版本，全面升级至动态图，支持20+分割模型，4个骨干网络，5个数据集，7种Loss：
+    * 分割模型：ANN, BiSeNetV2, DANet, DeeplabV3, DeeplabV3+, FCN, FastSCNN, Gated-scnn, GCNet, HarDNet, OCRNet, PSPNet, UNet, UNet++, U^2Net, Attention UNet、Decoupled SegNet、EMANet、DNLNet、ISANet
+    * 骨干网络：ResNet, HRNet, MobileNetV3, Xception
+    * 数据集：Cityscapes, ADE20K, Pascal VOC, Pascal Context, COCO Stuff
+    * Loss：CrossEntropy Loss、BootstrappedCrossEntropy Loss、Dice Loss、BCE Loss、OhemCrossEntropyLoss、RelaxBoundaryLoss、OhemEdgeAttentionLoss
+  * 提供基于Cityscapes和Pascal Voc数据集的高质量预训练模型 50+
+  * 支持多卡GPU并行评估，提供了高效的指标计算功能。支持多尺度评估/翻转评估/滑动窗口评估等多种评估方式。
+  * 支持XPU模型训练，包括DeepLabv3、HRNet、UNet。
+  * 开源了基于Hierarchical Multi-Scale Attention结构的语义分割模型，在Cityscapes验证集上达到87% mIoU。
+  * 动态图模式支持模型在线量化、剪枝等模型压缩功能。
+  * 动态图下支持模型动转静，实现高性能部署。
 
 * 2020.12.18