How to change the output shape of a semantic segmentation model?

[mMagmer]

You are trying to load pre-trained model weight to it.
Don’t need pre-trained weight
use :
deeplabv3_resnet50(weights=None,num_classes=1)
and if it’s necessary, try:

Removing classification layer for resnet101-deeplabv3

Would you like to remove the very last layer in this model or the complete classification head (DeepLabHead)? In the former case, you could just set model.classifier[4] to an nn.Identity layer: model = models.segmentation.deeplabv3_resnet101() model.classifier[4] = nn.Identity() If you would like to change this layer for a custom one using a new number of classes, just replace it with nn.Conv2d( in_channels=256, out_channels=nb_classes, kernel_size=1, stride=1 )