Monai Label: accuracy not showing

Support
, ,
1

Hi!
I’m currently training a new model using Monai Label.

I start using this configuration:

monailabel start_server --app apps/radiology --studies datasets/Task07_Pancreas/imagesTr --conf models deepedit --conf use_pretrained_model false

I have already submitted 26 labels, and the accuracy bar is still 0. Is that normal?

Thank you!

image
image651×712 22.1 KB

2

i get this error:

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DynUNet:
        size mismatch for input_block.conv1.conv.weight: copying a param with shape torch.Size([32, 5, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 2, 3, 3, 3]).
        size mismatch for input_block.conv3.conv.weight: copying a param with shape torch.Size([32, 5, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 2, 1, 1, 1]).
        size mismatch for output_block.conv.conv.weight: copying a param with shape torch.Size([4, 32, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 32, 1, 1, 1]).
        size mismatch for output_block.conv.conv.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([1]).
        size mismatch for skip_layers.downsample.conv1.conv.weight: copying a param with shape torch.Size([32, 5, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 2, 3, 3, 3]).
        size mismatch for skip_layers.downsample.conv3.conv.weight: copying a param with shape torch.Size([32, 5, 1, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 2, 1, 1, 1]).
[2024-05-07 11:00:27,144] [12688] [ThreadPoolExecutor-1_0] [INFO] (monailabel.utils.async_tasks.utils:83) - Return code: 1

i don’t know how to solve this