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.

Sign up for GitHub

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

Jump to bottom

训练时loss值很低，得到的模型形同虚设，检测不到目标 #206

Open

maige1219 opened this issue May 16, 2024 · 1 comment

maige1219 commented May 16, 2024

我想训练一个人脸检测的模型，从roboflow上找了一个数据集后以VOC格式下载了（但是它私自加上了后缀名）。

然后一步一步按照作者的步骤来进行的，结果训练时loss的值很奇怪，

而且使用得到的模型进行预测得不到任何结果，什么图进去，什么图出来。

望大佬相助

kkkkkkkb commented Jul 6, 2024

我觉得是数据集的问题，你可以让chatgpt写个代码把这些文件的后缀都去掉，然后再重新划分重新训练试试，感觉名字有时候太冗余也会出各种问题。（活着你查看下train.txt 2007_train.txt 等文件里面的文件名格式、地址都是对的吗

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment