YOLOV9 wts转换错误

[hu874]

Env

• GPU, e.g. RTX2080
• OS, e.g. Ubuntu20.04
• Cuda version
• TensorRT version 8.5.1

About this repo

• which branch/tag/commit are you using?
• which model? yolov5, retinaface?

Your problem

thon gen_wts.py -w yolov9-c.pt -o yolov9-c.wts Generating .wts for detect model Loading yolov9-c.pt YOLOv5 🚀 2024-3-4 Python-3.8.13 torch-1.8.1+cu111 CPU

Traceback (most recent call last): File "gen_wts.py", line 35, in model.model.float() AttributeError: 'dict' object has no attribute 'model' 使用官方yolov9-c进行的训练，.pt转.wts出现上面的问题

[wang-xinyu]

试下预训练的yolov9-c.pt?

[hu874]

使用了官方下载的预训练权重yolov9-c.pt依然报上方的错误。

[wang-xinyu]

@WuxinrongY 看下呢

[WuxinrongY]

35行修改为： model['model'].float()，随后我提交修改。

[hu874]

还有42和50行是否是要同步更改？

[hu874]

Generating .wts for detect model Loading yolov9-c.pt YOLOv5 🚀 2024-3-4 Python-3.8.13 torch-1.8.1+cu111 CPU

Traceback (most recent call last): File "gen_wts.py", line 39, in anchor_grid = model.model[-1].anchors * model.model[-1].stride[..., None, None] AttributeError: 'dict' object has no attribute 'model'

[hu874]

修改为： model['model']，全部更改以后报错：Generating .wts for detect model Loading yolov9-c.pt YOLOv5 🚀 2024-3-4 Python-3.8.13 torch-1.8.1+cu111 CPU

Traceback (most recent call last): File "gen_wts.py", line 39, in anchor_grid = model['model'][-1].anchors * model.model[-1].stride[..., None, None] TypeError: 'DetectionModel' object is not subscriptable

[WuxinrongY]

不好意思，写错了：35行：model = model['model'].float()

[WuxinrongY]

其他位置不修改。

[hu874]

使用最新版本tensorrtx进行engine转换时出现错误，并没有生成engine文件3/21/2024-14:21:36] [E] [TRT] 1: Unexpected exception _Map_base::at [03/21/2024-14:21:36] [E] [TRT] 2: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. ) Build engine successfully! yolov9: /home/tfboys/ws_usharing_102/TrafficLight/tensorrtx-master/yolov9/demo.cpp:31: void serialize_engine(unsigned int, std::__cxx11::string&, std::__cxx11::string&, std::__cxx11::string&): Assertion `serialized_engine != nullptr' failed.

[hu874]

使用官方预训练模型也是同样的报错

[wang-xinyu]

@WuxinrongY yolov9是不是最近有更新？ 最好能固定用一个他的分支

[WuxinrongY]

我测试中使用的是YOLOv9发布的0.1版本，你可以把错误发送到我的邮箱我看一下，[email protected]。

[hu874]

已发送，请查收

[WuxinrongY]

在int8模型中需要设置量化数据集路径，确认一下config.h中量化数据集路径设置是否正确，量化数据集需要设置为目录，末尾要加"/"，如"./calib/"。

[hu874]

Ok了

WuxinrongY @.***>于2024年3月22日 周五下午4:10写道：

在int8模型中需要设置量化数据集路径，确认一下config.h中量化数据集路径设置是否正确，量化数据集需要设置为目录，末尾要加"/"，如"./calib/"。

— Reply to this email directly, view it on GitHub https://github.com/wang-xinyu/tensorrtx/issues/1463#issuecomment-2014552324, or unsubscribe https://github.com/notifications/unsubscribe-auth/AR6FIIEMXPBLZU4S45BXHYDYZPRPZAVCNFSM6AAAAABFARLKV2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAMJUGU2TEMZSGQ . You are receiving this because you authored the thread.Message ID: @.***>

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.