encoder_depth error

[MykolaRobot]

Hi everyone! I am training model using DeepLabV3Plus architecture (mobilenetv2 encoder, imagenet weights).
When parameter encoder_depth = 5 - everything works ok.
But if encoder_depth = 4 or 3 the error occurs during training process.
Input image size is: (224,244)

Does anyone have the same problem? Or maybe someone can suggest a way to fix it.

[syyab]

I am facing the same problem with DeepLabV3Plus. It is only working with encoder_depth=5

[github-actions]

This issue is stale because it has been open 60 days with no activity. Remove stale label or comment or this will be closed in 7 days.

[github-actions]

This issue was closed because it has been stalled for 7 days with no activity.