-
Notifications
You must be signed in to change notification settings - Fork 276
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
Getting very low mIoU on Cityscapes #89
Comments
An update. I also tried downloading the provided trained model which is shared on the home page. Could you please guide me to find what I may be missing? |
@sreeragh-ar Thanks for your results. If the size of the input image is small, the network may not obtain enough context for classification when using predict_sliding(). The provided trained model was trained with 769x769 input size, using 769x769 as input size may be enough to obtain rich context information. When using predict_sliding(), the input size of the testing phase is the same as the training phase, which is good for better performance. It is a trade-off between the rich context and the consistency of training and testing settings. It's just my guess. Any discussion is welcome. |
@speedinghzl I have one more query. Downloaded official CCNet trained model and evaluated with official cityscapesScripts. But unable to reproduce the expected result.
Could you please share the exact |
Observed that mIoU is not improving beyond 28% on Cityscapes. (on the branch pytorch-1.1)
Changes made in run configs
I trained in different phases.
For eg. trained the model for 20,000 iterations. Evaluated the model and also recorded the learning rate after 20,000 iterations
Then restart training the model with
--restore-from ./snapshots/CS_scenes_20000.pth
LR={learning rate after 20000 iterations}
Am I missing something?
The text was updated successfully, but these errors were encountered: