add weights download

configs/ppyolo/README.md

@@ -60,7 +60,7 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods:
 - TensorRT FP16 inference speed testing exclude the time cost of bounding-box decoding(`yolo_box`) part comparing with FP32 testing above, which means that data reading, bounding-box decoding and post-processing(NMS) is excluded(test method same as [YOLOv4(AlexyAB)](https://github.com/AlexeyAB/darknet) too)
 - YOLOv4(AlexyAB) performance and inference speed is copy from single Tesla V100 testing results in [YOLOv4 github repo](https://github.com/AlexeyAB/darknet), Tesla V100 TensorRT FP16 inference speed is testing with tkDNN configuration and TensorRT 5.1.2.2 on single Tesla V100 based on [AlexyAB/darknet repo](https://github.com/AlexeyAB/darknet).
 - Download and configuration of YOLOv4(AlexyAB) is reproduced model of YOLOv4 in PaddleDetection, whose evaluation performance is same as YOLOv4(AlexyAB), and finetune training is supported in PaddleDetection currently, reproducing by training from backbone pretrain weights is on working, see [PaddleDetection YOLOv4](../yolov4/README.md) for details.
-- PP-YOLO trained with `batch_size=24` in each GPU with memory as 32G, configuation yml with `batch_size=12` which can be trained on GPU with memory as 16G is provided as `ppyolo_2x_bs12.yml`, training with `batch_size=12` reached `mAP(IoU=0.5:0.95) = 45.1%` on COCO val2017 dataset.
+- PP-YOLO trained with `batch_size=24` in each GPU with memory as 32G, configuation yml with `batch_size=12` which can be trained on GPU with memory as 16G is provided as `ppyolo_2x_bs12.yml`, training with `batch_size=12` reached `mAP(IoU=0.5:0.95) = 45.1%` on COCO val2017 dataset, download weights by [ppyolo_2x_bs12 model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_2x_bs12.pdparams)
 
 ### PP-YOLO for mobile
 

configs/ppyolo/README_cn.md

@@ -61,7 +61,7 @@ PP-YOLO从如下方面优化和提升YOLOv3模型的精度和速度：
 - YOLOv4(AlexyAB)模型精度和V100 FP32推理速度数据使用[YOLOv4 github库](https://github.com/AlexeyAB/darknet)提供的单卡V100上精度速度测试数据，V100 TensorRT FP16推理速度为使用[AlexyAB/darknet](https://github.com/AlexeyAB/darknet)库中tkDNN配置于单卡V100，TensorRT 5.1.2.2的测试结果。
 - PP-YOLO模型推理速度测试采用单卡V100，batch size=1进行测试，使用CUDA 10.2, CUDNN 7.5.1，TensorRT推理速度测试使用TensorRT 5.1.2.2。
 - YOLOv4(AlexyAB)行`模型下载`和`配置文件`为PaddleDetection复现的YOLOv4模型，目前评估精度已对齐，支持finetune，训练精度对齐中，可参见[PaddleDetection YOLOv4 模型](../yolov4/README.md)
-- PP-YOLO使用每GPU `batch_size=24`训练，需要使用显存为32G的GPU，我们也提供了`batch_size=12`的可以在显存为16G的GPU上训练的配置文件`ppyolo_2x_bs12.yml`，使用这个配置文件训练在COCO val2017数据集上评估结果为`mAP(IoU=0.5:0.95) = 45.1%`
+- PP-YOLO使用每GPU `batch_size=24`训练，需要使用显存为32G的GPU，我们也提供了`batch_size=12`的可以在显存为16G的GPU上训练的配置文件`ppyolo_2x_bs12.yml`，使用这个配置文件训练在COCO val2017数据集上评估结果为`mAP(IoU=0.5:0.95) = 45.1%`，可通过[ppyolo_2x_bs12模型](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_2x_bs12.pdparams)下载权重。
 
 ### PP-YOLO 移动端模型