search

WongKinYiu / yolov9

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
GNU General Public License v3.0
9.02k stars 1.43k forks source link

yolo.py:108: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! #591

Open HZW-WW opened 2 months ago

HZW-WW commented 2 months ago

/home/aaa/me/yolov9-main/models/yolo.py:108: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! elif self.dynamic or self.shape != shape:

When training the train_dual.py file, this warning was reported during training. Does it affect normal training? How to solve this problem? The problem seems to be line 229 of the yolo. py file: elif self.dynamic or self.shape != shape:

darkstar1227 commented 1 month ago

What is your system info.?

HZW-WW commented 1 month ago

您的系统信息是什么？

torch=1.12.1+cu113,python=3.8,linux system,Ubantu 20.04.3 LTS

darkstar1227 commented 3 weeks ago

您的系统信息是什么？

torch=1.12.1+cu113,python=3.8,linux system,Ubantu 20.04.3 LTS

It's seems to old.

HZW-WW commented 3 weeks ago

您的系统信息是什么？

torch=1.12.1+cu113,python=3.8,linux system,Ubantu 20.04.3 LTS

It's seems to old.

Do you mean the python version or the torch version?

darkstar1227 commented 3 weeks ago

您的系统信息是什么？

torch=1.12.1+cu113,python=3.8,linux system,Ubantu 20.04.3 LTS

It's seems to old.

Do you mean the python version or the torch version?

Torch and cuda. I suggest to use cuda 11.3 & torch 1.11.0 with pillow 9.5