zahrakhanjani128
commented
6 months ago Based on my conversation with the author through emails, and her guidance, I am providing more info here: Prepare your data_utils.py script according to your dataset. Use the correct parameters in config file for model training. Otherwise the pretrained model will give error. Thanks all especially the author of the rawnet baseline
Hello, could you please help me with RawNet2 baseline, I have this error when trying to apply the pre-trained model on another dataset and get scores:
--> 830 self.class.name, "\n\t".join(error_msgs))) 831 return _IncompatibleKeys(missing_keys, unexpected_keys) 832
RuntimeError: Error(s) in loading state_dict for RawNet: Unexpected key(s) in state_dict: "block2.0.conv_downsample.weight", "block2.0.conv_downsample.bias". size mismatch for block2.0.bn1.weight: copying a param with shape torch.Size([20]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for block2.0.bn1.bias: copying a param with shape torch.Size([20]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for block2.0.bn1.running_mean: copying a param with shape torch.Size([20]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for block2.0.bn1.running_var: copying a param with shape torch.Size([20]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for block2.0.conv1.weight: copying a param with shape torch.Size([128, 20, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3]).