mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 08:37:06 +08:00
c6d943b7f0
* 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 Co-authored-by: Jason <jiangjiajun@baidu.com>
简体中文 | English
YOLOv7 Prepare the model for Deployment
-
YOLOv7 deployment is based on YOLOv7 branching code, and COCO Pre-Trained Models.
- （1）The *.pt provided by the Official Library can be deployed after the [export ONNX model](#export ONNX model) operation; *.trt and *.pose models do not support deployment.
- （2）As for YOLOv7 model trained on customized data, please follow the operations guidelines in Export ONNX model and then refer to Detailed Deployment Tutorials to complete the deployment.
Export ONNX Model
# Download yolov7 model file
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
# Export onnx file (Tips: in accordance with YOLOv7 release v0.1 code)
python models/export.py --grid --dynamic --weights PATH/TO/yolov7.pt
# If your code supports exporting ONNX files with NMS, please use the following command to export ONNX files, then refer to the example of `yolov7end2end_ort` or `yolov7end2end_ort`
python models/export.py --grid --dynamic --end2end --weights PATH/TO/yolov7.pt
Download the pre-trained ONNX model
To facilitate testing for developers, we provide below the models exported by YOLOv7, which developers can download and use directly. (The accuracy of the models in the table is sourced from the official library)
| Model | Size | Accuracy |
|---|---|---|
| YOLOv7 | 141MB | 51.4% |
| YOLOv7x | 273MB | 53.1% |
| YOLOv7-w6 | 269MB | 54.9% |
| YOLOv7-e6 | 372MB | 56.0% |
| YOLOv7-d6 | 511MB | 56.6% |
| YOLOv7-e6e | 579MB | 56.8% |
Detailed Deployment Tutorials
Version
- This tutorial and related code are written based on YOLOv7 0.1