You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
I changed the backbone from vgg to resnet50. First, I have to use very low learning rate otherwise training diverges. Second, mAP is usually lower than vgg backbone adaptive teacher even if I train long. How can I achieve good performance with resnet50 backbone?
I am using gradient clipping and learning rate of 0.001 to stop diverging.
The text was updated successfully, but these errors were encountered:
By VGG you mean you train the model on the cityscapes dataset? The config file for clipart is using Resnet-101 and it is working. Replacing with ResNet50 should not be an issue with a similar config file.
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
I changed the backbone from vgg to resnet50. First, I have to use very low learning rate otherwise training diverges. Second, mAP is usually lower than vgg backbone adaptive teacher even if I train long. How can I achieve good performance with resnet50 backbone?
I am using gradient clipping and learning rate of 0.001 to stop diverging.
The text was updated successfully, but these errors were encountered: