Change encoder_depth in UNET

qubvel / segmentation_models.pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

https://smp.readthedocs.io/

MIT License

9.14k stars 1.63k forks source link

Change encoder_depth in UNET #809

Closed nafe93 closed 7 months ago

nafe93 commented 10 months ago

Is it possible to change the depth in any way, I don’t really want to break a good library.

As far as I understand there are restrictions.

model = smp.Unet( encoder_name="lol", encoder_weights="lol", activation="sigmoid", in_channels=3, classes=1, encoder_depth=6, decoder_channels=(256, 128, 64, 32, 16, 8),

).to(device)

github-actions[bot] commented 8 months ago

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[bot] commented 7 months ago

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