CT segmentation fail

[TanjaLe]

CT segmentierung bricht ab:

RuntimeError: Error(s) in loading state_dict for PlainConvUNet:
size mismatch for decoder.seg_layers.0.weight: copying a param with shape torch.Size([10, 320, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([11, 320, 1, 1, 1]).
size mismatch for decoder.seg_layers.0.bias: copying a param with shape torch.Size([10]) from checkpoint, the shape in current model is torch.Size([11]).
size mismatch for decoder.seg_layers.1.weight: copying a param with shape torch.Size([10, 256, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([11, 256, 1, 1, 1]).
size mismatch for decoder.seg_layers.1.bias: copying a param with shape torch.Size([10]) from checkpoint, the shape in current model is torch.Size([11]).
size mismatch for decoder.seg_layers.2.weight: copying a param with shape torch.Size([10, 128, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([11, 128, 1, 1, 1]).
size mismatch for decoder.seg_layers.2.bias: copying a param with shape torch.Size([10]) from checkpoint, the shape in current model is torch.Size([11]).
size mismatch for decoder.seg_layers.3.weight: copying a param with shape torch.Size([10, 64, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([11, 64, 1, 1, 1]).
size mismatch for decoder.seg_layers.3.bias: copying a param with shape torch.Size([10]) from checkpoint, the shape in current model is torch.Size([11]).
size mismatch for decoder.seg_layers.4.weight: copying a param with shape torch.Size([10, 32, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([11, 32, 1, 1, 1]).
size mismatch for decoder.seg_layers.4.bias: copying a param with shape torch.Size([10]) from checkpoint, the shape in current model is torch.Size([11]).