update map_fps.png (#1669)

README_cn.md

@@ -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

README_en.md

@@ -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.**