Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

加载自定义模型闪退 #9

Closed
Yuko1997 opened this issue Jun 15, 2023 · 5 comments
Closed

加载自定义模型闪退 #9

Yuko1997 opened this issue Jun 15, 2023 · 5 comments
Labels
bug Something isn't working

Comments

@Yuko1997
Copy link

没有任何报错或提示,程序直接退出
type: test
name: testA
display_name: Test
model_path: ‪D:/Auto/best.onnx
input_width: 640
input_height: 640
score_threshold: 0.45
classes:

  • enemy
  • friend
@CVHub520
Copy link
Owner

您好,配置文件参数有误,type 字段为指定模型类型的标识符,目前支持:["segment_anything", "yolov5", "yolov6", "yolov7", "yolov8", "yolox", "yolov5_cls", "yolov6_face", "rtdetr"],不可自定义。

@CVHub520 CVHub520 added the bug Something isn't working label Jun 16, 2023
@Yuko1997
Copy link
Author

您好,配置文件参数有误, 字段为指定模型类型的标识符,目前支持:[“segment_anything”, “yolov5”, “yolov6”, “yolov7”, “yolov8”, “yolox”, “yolov5_cls”, “yolov6_face”, “rtdetr”],不可自定义。type

你好,现在提示这个,是模型有要求吗,直接用yolov8自带命令导出onnx的
20230616114047

@CVHub520
Copy link
Owner

您好,配置文件参数有误, 字段为指定模型类型的标识符,目前支持:[“segment_anything”, “yolov5”, “yolov6”, “yolov7”, “yolov8”, “yolox”, “yolov5_cls”, “yolov6_face”, “rtdetr”],不可自定义。type

你好,现在提示这个,是模型有要求吗,直接用yolov8自带命令导出onnx的 20230616114047

可以先下载 release 版本的 yolov8-onnx 模型,用 netron 对比下两个模型。解决不了的话可将模型和配置文件打个压缩包传到网盘发个链接给我看看。

@Yuko1997
Copy link
Author

您好,配置文件参数有误, 字段为指定模型类型的标识符,目前支持:[“segment_anything”, “yolov5”, “yolov6”, “yolov7”, “yolov8”, “yolox”, “yolov5_cls”, “yolov6_face”, “rtdetr”],不可自定义。type

你好,现在提示这个,是模型有要求吗,直接用yolov8自带命令导出onnx的 20230616114047

可以先下载 release 版本的 yolov8-onnx 模型,用 netron 对比下两个模型。解决不了的话可将模型和配置文件打个压缩包传到网盘发个链接给我看看。

这里有些区别
20230616233323
20230616233331
模型和配置https://wwut.lanzoul.com/ii7av0zboj7c

@CVHub520
Copy link
Owner

@Yuko1997 您好,这边复现了下发现是 onnx 与 opencv 和 torch 版本的兼容问题,请确保 torch <= 1.11,并修改 opset 版本(默认是 14):

# pip install ultralytics 
from ultralytics import YOLO

model = YOLO("yolov8n.yaml")  # build a new model from scratch
model = YOLO("yolov8n.pt")  # load a pretrained model (recommended for training)

path = model.export(format="onnx", opset=12)  # export the model to ONNX format

测试版本为:torch==1.11.0 | opencv-python==4.6.0.66 | onnx==1.12.0

后续会对多版本做兼容,敬请留意,再次感谢您的关注与支持。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

2 participants