diff --git a/README_cn.md b/README_cn.md index d09eddbae03bdf79e795ba3f67af0e0d46447a99..46a37babec7f07ba3e2b70fd7e5256b253bae0ef 100644 --- a/README_cn.md +++ b/README_cn.md @@ -181,7 +181,7 @@ PaddleDetection模块化地实现了多种主流目标检测算法,提供了 - `CBResNet`为`Cascade-Faster-RCNN-CBResNet200vd-FPN`模型,COCO数据集mAP高达53.3% - `Cascade-Faster-RCNN`为`Cascade-Faster-RCNN-ResNet50vd-DCN`,PaddleDetection将其优化到COCO数据mAP为47.8%时推理速度为20FPS - `PP-YOLO`在COCO数据集精度45.9%,Tesla V100预测速度72.9FPS,精度速度均优于[YOLOv4](https://arxiv.org/abs/2004.10934) -- `PP-YOLO v2`是对`PP-YOLO`模型的进一步优化,在COCO数据集精度49.5%,Tesla V100预测速度60FPS +- `PP-YOLO v2`是对`PP-YOLO`模型的进一步优化,在COCO数据集精度49.5%,Tesla V100预测速度68.9FPS - 图中模型均可在[模型库](#模型库)中获取 ## 文档教程 diff --git a/docs/images/fps_map.png b/docs/images/fps_map.png index 825ce201c5b728a62a0672e85f5e90e3977cec79..d73877729c0775709e5954c008a88776bf48606a 100644 Binary files a/docs/images/fps_map.png and b/docs/images/fps_map.png differ