-
Notifications
You must be signed in to change notification settings - Fork 1.7k
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
训练集和测试结果类别不一致 #3433
Comments
是不是模型的num_classes参数没有改 |
在配置文件.yml文件中,已经改了,num_classes = 12, 0代表背景,1~11是各个物体 |
请给出配置文件内容、训练命令、测试命令 |
配置文件: train_dataset: val_dataset: optimizer: lr_scheduler: loss: model: 训练命令: 测试命令: |
找到问题了,我修改了tools/predict.py中的写入方式,我希望得到原始的预测结果(变量pred),我将未经处理的pred写为图像,格式为.jpg时出现了上述问题,换成.png就好了。 代码如下 my
感谢您的解答! |
问题确认 Search before asking
请提出你的问题 Please ask your question
您好,我在训练集中一共有11个类别,训练好模型后进行测试时,发现类别除了0
11外,还有类别12,13,14,15,多了4个类别,不知道是什么原因造成的?类别011分割都很准确,类别12~15发现是一些零星的边缘线The text was updated successfully, but these errors were encountered: