-
Notifications
You must be signed in to change notification settings - Fork 90
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
Results for VOC2012 are not correct #51
Comments
Restored model parameters from model_0827/model.ckpt-20000 |
"RuntimeWarning: divide by zero encountered in long_scalars" Obviously, there is something wrong with your label images. |
First, check that your label images are composed of pixels with integer values between [0,20]. One thing that I'm pretty sure is that using ResNet-101 slim checkpoint is fine and will not cause problems. |
I Use the original images from VOC2012 for training.
training set: 1464
test set : 1449
At the same time , I use the Res101 for pre-train model which is from slim's checkpoint.
The loss for training is about 1.8
when I test the model, the IOU is very low , only 0.1 and some classes are nan,
What's wrong with my configuration ? I have modified the environment with README
The text was updated successfully, but these errors were encountered: