未验证 提交 6f15306d 编写于 作者: K Kaipeng Deng 提交者: GitHub

update map_fps.png (#1669)

上级 86ac0510
......@@ -18,7 +18,7 @@ PaddleDetection模块化地实现了多种主流目标检测算法,提供了
- 2020.09.30: 发布[移动端检测demo](deploy/android_demo),可直接扫码安装体验。
- 2020.09.21-27: 【目标检测7日打卡课】手把手教你从入门到进阶,深入了解目标检测算法的前世今生。立即加入课程QQ交流群(1136406895)一起学习吧 :)
- 2020.07.24: 发布**产业最实用**目标检测模型 [PP-YOLO](https://arxiv.org/abs/2007.12099) ,深入考虑产业应用对精度速度的双重面诉求,COCO数据集精度45.2%,Tesla V100预测速度72.9 FPS,详细信息见[文档](configs/ppyolo/README_cn.md)
- 2020.07.24: 发布**产业最实用**目标检测模型 [PP-YOLO](https://arxiv.org/abs/2007.12099) ,深入考虑产业应用对精度速度的双重面诉求,COCO数据集精度45.2%(最新45.9%),Tesla V100预测速度72.9 FPS,详细信息见[文档](configs/ppyolo/README_cn.md)
- 2020.06.11: 发布676类大规模服务器端实用目标检测模型,适用于绝大部分使用场景,可以直接用来预测,也可以用于微调其他任务。
### 特性
......
......@@ -13,8 +13,8 @@ image object detection, and automatic inspection with its practical features suc
and multi-platform deployment.
[PP-YOLO](https://arxiv.org/abs/2007.12099), which is faster and has higer performance than YOLOv4,
has been released, it reached mAP(0.5:0.95) as 45.2% on COCO test2019 dataset and 72.9 FPS on single
Test V100. Please refer to [PP-YOLO](configs/ppyolo/README.md) for details.
has been released, it reached mAP(0.5:0.95) as 45.2%(newest 45.9%) on COCO test2019 dataset and
72.9 FPS on single Test V100. Please refer to [PP-YOLO](configs/ppyolo/README.md) for details.
**Now all models in PaddleDetection require PaddlePaddle version 1.8 or higher, or suitable develop version.**
......
docs/images/map_fps.png

384.1 KB | W: | H:

docs/images/map_fps.png

401.3 KB | W: | H:

docs/images/map_fps.png
docs/images/map_fps.png
docs/images/map_fps.png
docs/images/map_fps.png
  • 2-up
  • Swipe
  • Onion skin
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