Files
FastDeploy/examples/vision/detection/yolov5
WJJ1995 6e79df40d9 [Model] Update YOLOv5 from 6.0 to 7.0 version (#890)
* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* integrated x2paddle

* add model convert readme

* update readme

* re-lint

* add processor api

* Add MattingResult Free

* change valid_cpu_backends order

* add ppocr benchmark

* mv bs from 64 to 32

* fixed quantize.md

* fixed quantize bugs

* Add Monitor for benchmark

* update mem monitor

* Set trt_max_batch_size default 1

* fixed ocr benchmark bug

* support yolov5 in serving

* Fixed yolov5 serving

* Fixed postprocess

* update yolov5 to 7.0

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-12-15 17:23:27 +08:00
..
2022-12-13 11:53:36 +08:00
2022-12-13 11:53:36 +08:00

YOLOv5准备部署模型

  • YOLOv5 v7.0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 v7.0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 7.6MB 28.0%
YOLOv5s 28MB 37.4%
YOLOv5m 82MB 45.4%
YOLOv5l 178MB 49.0%
YOLOv5x 332MB 50.7%

详细部署文档

版本说明