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

tt100k yolov5up6 训练报错 #159

Open
1 task done
hbo-lambda opened this issue Jun 15, 2023 · 3 comments
Open
1 task done

tt100k yolov5up6 训练报错 #159

hbo-lambda opened this issue Jun 15, 2023 · 3 comments
Assignees

Comments

@hbo-lambda
Copy link

hbo-lambda commented Jun 15, 2023

问题确认 Search before asking

  • 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

ubuntu 20.04
paddle 2.4.2
nvidia 单卡 v100 32G

执行命令:

python tools/train.py -c configs/yolov5u/yolov5up6_s_300e_coco.yml --eval --amp

调整了数据集的样本数量,使用roadsign_voc,样本数量少于32的时候会报错。所以自己选取原样本中35个样本去测试,我的标签数量是250个,抽取的样本尺寸是2048*2048。yolov5up6_s_300e_coco.yml 相关的配置,除了数据集路径外,其他没做改动。抽取的样本如链接: https://pan.baidu.com/s/1TvUUjSGGShppZAnewPURPA?pwd=cnen 提取码: cnen

报错如下:
Snip20230615_5

@nemonameless
Copy link
Collaborator

请先尝试yolov5s或别的模型,如果也报同样的错,则可认为是数据集制作的问题。

@mutouoa
Copy link

mutouoa commented Jun 29, 2023

@nemonameless 出现同样的问题,也已在其他模型训练过

@nemonameless
Copy link
Collaborator

你好,如还需要帮看下问题的话还请提供下您的数据集。库里的模型是在coco voc上验证过的,应该是大部分数据集边界情况都覆盖了。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants