DiffusionModelEncoder output layer is set outside of the initiation and left out of trainable parameters and set to the wrong device #8577
Description
Describe the bug
This issue has been observed in the tutorials: Project-MONAI/tutorials#2030 (comment).
Expected behavior
The out layer should not be set in the forward loop because:
- The device is wrong in this scenario
- The parameters from this layer are not included in the optimizer trainable args.
Additional context
This was caused by fix #8514.
Activity
Diffusion Model Encoder has an output layer set in forward method and…
Diffusion Model Encoder has an output layer set in forward method and…
Diffusion Model Encoder has an output layer set in forward method and…