apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
376fdbfe2c40d966416638dfa30a6bb092468461
FastDeploy/examples/vision/detection/yolov5
History
huangjianhui 376fdbfe2c [Other] Update old Api to new ones (#861) 
* Update keypointdetection result docs

* Update im.copy() to im in examples

* Update new Api, fastdeploy::vision::Visualize to fastdeploy::vision

* Update SwapBackgroundSegmentation && SwapBackgroundMatting to SwapBackground

* Update README_CN.md

* Update README_CN.md
2022-12-14 17:25:58 +08:00
..
a311d
[Backend] A311D support (#825)
2022-12-13 11:53:36 +08:00
cpp
[Other] Update old Api to new ones (#861)
2022-12-14 17:25:58 +08:00
python
[Other]Update im.copy() to im in examples (#854)
2022-12-12 09:47:54 +08:00
quantize
[Other] Update old Api to new ones (#861)
2022-12-14 17:25:58 +08:00
rv1126
[Backend] A311D support (#825)
2022-12-13 11:53:36 +08:00
serving
[Serving] Fixed preprocess&&postprocess in YOLOv5 Serving (#874)
2022-12-14 10:14:29 +08:00
README.md
[Doc]Fix doc error (#539)
2022-11-09 13:57:02 +08:00

README.md

YOLOv5准备部署模型

  • YOLOv5 v6.0部署模型实现来自YOLOv5,和基于COCO的预训练模型
    • （1）官方库提供的*.onnx可直接进行部署；
    • （2）开发者基于自己数据训练的YOLOv5 v6.0模型，可使用YOLOv5中的export.py导出ONNX文件后，完成部署。

下载预训练ONNX模型

为了方便开发者的测试，下面提供了YOLOv5导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）

模型 大小 精度
YOLOv5n 7.5MB 28.4%
YOLOv5s 28.9MB 37.2%
YOLOv5m 84.7MB 45.2%
YOLOv5l 186.2MB 48.8%
YOLOv5x 346.9MB 50.7%

详细部署文档

版本说明