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

判断最佳模型的条件,以及设置停止条件 #45

Open
lipeng1109 opened this issue Nov 30, 2020 · 2 comments
Open

判断最佳模型的条件,以及设置停止条件 #45

lipeng1109 opened this issue Nov 30, 2020 · 2 comments

Comments

@lipeng1109
Copy link

您好,我最近用您这个做了一个简单的检测箱子的模型,开始5000次保存的模型感觉效果还行,就一直训练着,现在训练到46000次,发现模型效果反而变得很差,查看日志,损失函数期间从降低一直到再次升高,但最终损失函数还是蛮小的,不知道有没有一个比较好的参考值,比如说mAP达到多少,我的任务相对简单,评测mAP大的时候有0.68的样子;后续一直训练,最终最佳模型mAP能达到0.8的样子,实际效果却很不理想了

@lipeng1109
Copy link
Author

企业微信截图_20201130120159

最新评测结果,里面有-1代表的是未识别到吗

@lipeng1109
Copy link
Author

发现原因为我读取的图片为中文名称,将读取方式有cv2.imread方式变为cv2.imdecode方式,没注意按照这种方式来了,读取图片与imread不一样image = cv2.imdecode(np.fromfile(image_path + filename,dtype=np.uint8),-1)
需要这样读取:image = cv2.imdecode(np.fromfile(image_path + filename,dtype=np.uint8),cv2.IMREAD_COLOR) 网上部分教程有误导嫌疑

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

1 participant