diff --git a/demo/auto_compression/detection/README.md b/demo/auto_compression/detection/README.md index 31fb524f90fe03c8b37682c84f4ed210839d22bb..d1e9c7d8538e74709ad81dbe71bf3af82002041e 100644 --- a/demo/auto_compression/detection/README.md +++ b/demo/auto_compression/detection/README.md @@ -20,23 +20,23 @@ ### PP-YOLOE -| 模型 | 策略 | 输入尺寸 | mAPval
0.5:0.95 | 预测时延FP32
(ms) |预测时延FP32
(ms) | 预测时延INT8
(ms) | 配置文件 | Inference模型 | +| 模型 | 策略 | 输入尺寸 | mAPval
0.5:0.95 | 预测时延FP32
(ms) |预测时延FP16
(ms) | 预测时延INT8
(ms) | 配置文件 | Inference模型 | | :-------- |:-------- |:--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: | :-----------------------------: | | PP-YOLOE-l | Base模型 | 640*640 | 50.9 | 11.2 | 7.7ms | - | [config](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/detection/ppyoloe_crn_l_300e_coco.tar) | | PP-YOLOE-l | 量化+蒸馏 | 640*640 | 50.6 | - | - | 6.7ms | [config](https://github.com/PaddlePaddle/PaddleSlim/tree/develop/demo/auto_compression/detection/configs/ppyoloe_l_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/ppyoloe_crn_l_300e_coco_quant.tar) | - mAP的指标均在COCO val2017数据集中评测得到。 -- PP-YOLOE模型在Tesla V100的GPU环境下测试,测试脚本是[benchmark demo](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/deploy/python) +- PP-YOLOE模型在Tesla V100的GPU环境下测试,并且开启TensorRT,测试脚本是[benchmark demo](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/deploy/python) ### YOLOv5 -| 模型 | 策略 | 输入尺寸 | mAPval
0.5:0.95 | 预测时延FP32
(ms) |预测时延FP32
(ms) | 预测时延INT8
(ms) | 配置文件 | Inference模型 | +| 模型 | 策略 | 输入尺寸 | mAPval
0.5:0.95 | 预测时延FP32
(ms) |预测时延FP16
(ms) | 预测时延INT8
(ms) | 配置文件 | Inference模型 | | :-------- |:-------- |:--------: | :---------------------: | :----------------: | :----------------: | :---------------: | :-----------------------------: | :-----------------------------: | | YOLOv5s | Base模型 | 640*640 | 37.4 | 6.0 | 4.9ms | - | - | [Model](https://bj.bcebos.com/v1/paddle-slim-models/detection/yolov5s_infer.tar) | | YOLOv5s | 量化+蒸馏 | 640*640 | 36.5 | - | - | 4.5ms | [config](https://github.com/PaddlePaddle/PaddleSlim/tree/develop/demo/auto_compression/detection/configs/yolov5s_qat_dis.yaml) | [Model](https://bj.bcebos.com/v1/paddle-slim-models/act/yolov5s_quant.tar) | 说明: - mAP的指标均在COCO val2017数据集中评测得到。 -- YOLOv5s模型在Tesla V100的GPU环境下测试,测试脚本是[benchmark demo](./infer.py) +- YOLOv5s模型在Tesla V100的GPU环境下测试,并且开启TensorRT,测试脚本是[benchmark demo](./infer.py) - YOLOv5模型源自[ultralytics/yolov5](https://github.com/ultralytics/yolov5),通过[X2Paddle](https://github.com/PaddlePaddle/X2Paddle)工具转换YOLOv5预测模型步骤: (1) 安装X2Paddle的1.3.6以上版本;(pip install x2paddle)