MaGGIe issues

pretrained model shape don’t match with model definition

1

raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for MaGGIe_Temp: size mismatch for decoder.dummy_downscale.0.weight: copying a param with shape torch.Size([32, 3, 3, 3]) from checkpoint, the...

josh-zhu

training error

when I am trying to train Maggie, it always encounters the followed issues: **[rank3]: tokens, atten_mat = self.token_feat_ca_layers[i]( [rank3]: File "/home/kemove/anaconda3/envs/vitmat/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl [rank3]: return self._call_impl(*args, **kwargs) [rank3]:...

kingbackyang