pytorch-auto-drive icon indicating copy to clipboard operation
pytorch-auto-drive copied to clipboard

Resnet101 SCNN pretrained weights

Open yigitbalcioglu opened this issue 8 months ago • 1 comments

I don't know why but I tried many weights and I get many missing keys error. This problem is not about prefixes, I am sure I miss something.

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for _SimpleSegmentationModel: Missing key(s) in state_dict: "backbone.conv1.weight", "backbone.bn1.weight", "backbone.bn1.bias", "backbone.bn1.running_mean", "backbone.bn1.running_var", "backbone.layer1.0.conv1.weight", "backbone.layer1.0.bn1.weight", "backbone.layer1.0.bn1.bias", "backbone.layer1.0.bn1.running_mean", "backbone.layer1.0.bn1.running_var",

It goes on like this

yigitbalcioglu avatar Mar 18 '25 14:03 yigitbalcioglu

@yigitbalcioglu Hi, exactly which config and command did you run?

voldemortX avatar Mar 20 '25 01:03 voldemortX