Skip to content

Instantly share code, notes, and snippets.

@albusdemens
Created February 14, 2020 10:39
Show Gist options
  • Select an option

  • Save albusdemens/170905c5f565d318443e79d8f21dbb64 to your computer and use it in GitHub Desktop.

Select an option

Save albusdemens/170905c5f565d318443e79d8f21dbb64 to your computer and use it in GitHub Desktop.
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for StyleGAN2:
Unexpected key(s) in state_dict: "G.blocks.6.to_style1.weight", "G.blocks.6.to_style1.bias", "G.blocks.6.to_noise1.weight", "G.blocks.6.to_noise1.bias", "G.blocks.6.conv1.weight", "G.blocks.6.to_style2.weight", "G.blocks.6.to_style2.bias", "G.blocks.6.to_noise2.weight", "G.blocks.6.to_noise2.bias", "G.blocks.6.conv2.weight", "G.blocks.6.to_rgb.to_style.weight", "G.blocks.6.to_rgb.to_style.bias", "G.blocks.6.to_rgb.conv.weight", "G.blocks.7.to_style1.weight", "G.blocks.7.to_style1.bias", "G.blocks.7.to_noise1.weight", "G.blocks.7.to_noise1.bias", "G.blocks.7.conv1.weight", "G.blocks.7.to_style2.weight", "G.blocks.7.to_style2.bias", "G.blocks.7.to_noise2.weight", "G.blocks.7.to_noise2.bias", "G.blocks.7.conv2.weight", "G.blocks.7.to_rgb.to_style.weight", "G.blocks.7.to_rgb.to_style.bias", "G.blocks.7.to_rgb.conv.weight", "D.blocks.7.conv_res.weight", "D.blocks.7.conv_res.bias", "D.blocks.7.net.0.weight", "D.blocks.7.net.0.bias", "D.blocks.7.net.2.weight", "D.blocks.7.net.2.bias", "D.blocks.7.downsample.weight", "D.blocks.7.downsample.bias", "D.blocks.8.conv_res.weight", "D.blocks.8.conv_res.bias", "D.blocks.8.net.0.weight", "D.blocks.8.net.0.bias", "D.blocks.8.net.2.weight", "D.blocks.8.net.2.bias", "D.blocks.6.downsample.weight", "D.blocks.6.downsample.bias", "GE.blocks.6.to_style1.weight", "GE.blocks.6.to_style1.bias", "GE.blocks.6.to_noise1.weight", "GE.blocks.6.to_noise1.bias", "GE.blocks.6.conv1.weight", "GE.blocks.6.to_style2.weight", "GE.blocks.6.to_style2.bias", "GE.blocks.6.to_noise2.weight", "GE.blocks.6.to_noise2.bias", "GE.blocks.6.conv2.weight", "GE.blocks.6.to_rgb.to_style.weight", "GE.blocks.6.to_rgb.to_style.bias", "GE.blocks.6.to_rgb.conv.weight", "GE.blocks.7.to_style1.weight", "GE.blocks.7.to_style1.bias", "GE.blocks.7.to_noise1.weight", "GE.blocks.7.to_noise1.bias", "GE.blocks.7.conv1.weight", "GE.blocks.7.to_style2.weight", "GE.blocks.7.to_style2.bias", "GE.blocks.7.to_noise2.weight", "GE.blocks.7.to_noise2.bias", "GE.blocks.7.conv2.weight", "GE.blocks.7.to_rgb.to_style.weight", "GE.blocks.7.to_rgb.to_style.bias", "GE.blocks.7.to_rgb.conv.weight".
size mismatch for G.initial_block: copying a param with shape torch.Size([8, 4, 4]) from checkpoint, the shape in current model is torch.Size([64, 4, 4]).
size mismatch for G.blocks.0.to_style1.weight: copying a param with shape torch.Size([8, 512]) from checkpoint, the shape in current model is torch.Size([64, 512]).
size mismatch for G.blocks.0.to_style1.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for G.blocks.0.to_noise1.weight: copying a param with shape torch.Size([512, 1]) from checkpoint, the shape in current model is torch.Size([1024, 1]).
size mismatch for G.blocks.0.to_noise1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G.blocks.0.conv1.weight: copying a param with shape torch.Size([512, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 64, 3, 3]).
size mismatch for G.blocks.0.to_style2.weight: copying a param with shape torch.Size([512, 512]) from checkpoint, the shape in current model is torch.Size([1024, 512]).
size mismatch for G.blocks.0.to_style2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G.blocks.0.to_noise2.weight: copying a param with shape torch.Size([512, 1]) from checkpoint, the shape in current model is torch.Size([1024, 1]).
size mismatch for G.blocks.0.to_noise2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G.blocks.0.conv2.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for G.blocks.0.to_rgb.to_style.weight: copying a param with shape torch.Size([512, 512]) from checkpoint, the shape in current model is torch.Size([1024, 512]).
size mismatch for G.blocks.0.to_rgb.to_style.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G.blocks.0.to_rgb.conv.weight: copying a param with shape torch.Size([3, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 1024, 1, 1]).
size mismatch for G.blocks.1.to_style1.weight: copying a param with shape torch.Size([512, 512]) from checkpoint, the shape in current model is torch.Size([1024, 512]).
size mismatch for G.blocks.1.to_style1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G.blocks.1.to_noise1.weight: copying a param with shape torch.Size([256, 1]) from checkpoint, the shape in current model is torch.Size([512, 1]).
size mismatch for G.blocks.1.to_noise1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for G.blocks.1.conv1.weight: copying a param with shape torch.Size([256, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 1024, 3, 3]).
size mismatch for G.blocks.1.to_style2.weight: copying a param with shape torch.Size([256, 512]) from checkpoint, the shape in current model is torch.Size([512, 512]).
size mismatch for G.blocks.1.to_style2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for G.blocks.1.to_noise2.weight: copying a param with shape torch.Size([256, 1]) from checkpoint, the shape in current model is torch.Size([512, 1]).
size mismatch for G.blocks.1.to_noise2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for G.blocks.1.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 512, 3, 3]).
size mismatch for G.blocks.1.to_rgb.to_style.weight: copying a param with shape torch.Size([256, 512]) from checkpoint, the shape in current model is torch.Size([512, 512]).
size mismatch for G.blocks.1.to_rgb.to_style.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for G.blocks.1.to_rgb.conv.weight: copying a param with shape torch.Size([3, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 512, 1, 1]).
size mismatch for G.blocks.2.to_style1.weight: copying a param with shape torch.Size([256, 512]) from checkpoint, the shape in current model is torch.Size([512, 512]).
size mismatch for G.blocks.2.to_style1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for G.blocks.2.to_noise1.weight: copying a param with shape torch.Size([128, 1]) from checkpoint, the shape in current model is torch.Size([256, 1]).
size mismatch for G.blocks.2.to_noise1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for G.blocks.2.conv1.weight: copying a param with shape torch.Size([128, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 512, 3, 3]).
size mismatch for G.blocks.2.to_style2.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for G.blocks.2.to_style2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for G.blocks.2.to_noise2.weight: copying a param with shape torch.Size([128, 1]) from checkpoint, the shape in current model is torch.Size([256, 1]).
size mismatch for G.blocks.2.to_noise2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for G.blocks.2.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 256, 3, 3]).
size mismatch for G.blocks.2.to_rgb.to_style.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for G.blocks.2.to_rgb.to_style.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for G.blocks.2.to_rgb.conv.weight: copying a param with shape torch.Size([3, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 256, 1, 1]).
size mismatch for G.blocks.3.to_style1.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for G.blocks.3.to_style1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for G.blocks.3.to_noise1.weight: copying a param with shape torch.Size([64, 1]) from checkpoint, the shape in current model is torch.Size([128, 1]).
size mismatch for G.blocks.3.to_noise1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for G.blocks.3.conv1.weight: copying a param with shape torch.Size([64, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 256, 3, 3]).
size mismatch for G.blocks.3.to_style2.weight: copying a param with shape torch.Size([64, 512]) from checkpoint, the shape in current model is torch.Size([128, 512]).
size mismatch for G.blocks.3.to_style2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for G.blocks.3.to_noise2.weight: copying a param with shape torch.Size([64, 1]) from checkpoint, the shape in current model is torch.Size([128, 1]).
size mismatch for G.blocks.3.to_noise2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for G.blocks.3.conv2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for G.blocks.3.to_rgb.to_style.weight: copying a param with shape torch.Size([64, 512]) from checkpoint, the shape in current model is torch.Size([128, 512]).
size mismatch for G.blocks.3.to_rgb.to_style.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for G.blocks.3.to_rgb.conv.weight: copying a param with shape torch.Size([3, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 128, 1, 1]).
size mismatch for G.blocks.4.to_style1.weight: copying a param with shape torch.Size([64, 512]) from checkpoint, the shape in current model is torch.Size([128, 512]).
size mismatch for G.blocks.4.to_style1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for G.blocks.4.to_noise1.weight: copying a param with shape torch.Size([32, 1]) from checkpoint, the shape in current model is torch.Size([64, 1]).
size mismatch for G.blocks.4.to_noise1.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for G.blocks.4.conv1.weight: copying a param with shape torch.Size([32, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 128, 3, 3]).
size mismatch for G.blocks.4.to_style2.weight: copying a param with shape torch.Size([32, 512]) from checkpoint, the shape in current model is torch.Size([64, 512]).
size mismatch for G.blocks.4.to_style2.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for G.blocks.4.to_noise2.weight: copying a param with shape torch.Size([32, 1]) from checkpoint, the shape in current model is torch.Size([64, 1]).
size mismatch for G.blocks.4.to_noise2.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for G.blocks.4.conv2.weight: copying a param with shape torch.Size([32, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for G.blocks.4.to_rgb.to_style.weight: copying a param with shape torch.Size([32, 512]) from checkpoint, the shape in current model is torch.Size([64, 512]).
size mismatch for G.blocks.4.to_rgb.to_style.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for G.blocks.4.to_rgb.conv.weight: copying a param with shape torch.Size([3, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 64, 1, 1]).
size mismatch for G.blocks.5.to_style1.weight: copying a param with shape torch.Size([32, 512]) from checkpoint, the shape in current model is torch.Size([64, 512]).
size mismatch for G.blocks.5.to_style1.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for G.blocks.5.to_noise1.weight: copying a param with shape torch.Size([16, 1]) from checkpoint, the shape in current model is torch.Size([32, 1]).
size mismatch for G.blocks.5.to_noise1.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for G.blocks.5.conv1.weight: copying a param with shape torch.Size([16, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 64, 3, 3]).
size mismatch for G.blocks.5.to_style2.weight: copying a param with shape torch.Size([16, 512]) from checkpoint, the shape in current model is torch.Size([32, 512]).
size mismatch for G.blocks.5.to_style2.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for G.blocks.5.to_noise2.weight: copying a param with shape torch.Size([16, 1]) from checkpoint, the shape in current model is torch.Size([32, 1]).
size mismatch for G.blocks.5.to_noise2.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for G.blocks.5.conv2.weight: copying a param with shape torch.Size([16, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]).
size mismatch for G.blocks.5.to_rgb.to_style.weight: copying a param with shape torch.Size([16, 512]) from checkpoint, the shape in current model is torch.Size([32, 512]).
size mismatch for G.blocks.5.to_rgb.to_style.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for G.blocks.5.to_rgb.conv.weight: copying a param with shape torch.Size([3, 16, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 32, 1, 1]).
size mismatch for D.blocks.0.conv_res.weight: copying a param with shape torch.Size([2, 3, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 3, 1, 1]).
size mismatch for D.blocks.0.conv_res.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for D.blocks.0.net.0.weight: copying a param with shape torch.Size([2, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3]).
size mismatch for D.blocks.0.net.0.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for D.blocks.0.net.2.weight: copying a param with shape torch.Size([2, 2, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 16, 3, 3]).
size mismatch for D.blocks.0.net.2.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for D.blocks.0.downsample.weight: copying a param with shape torch.Size([2, 2, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 16, 3, 3]).
size mismatch for D.blocks.0.downsample.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([16]).
size mismatch for D.blocks.1.conv_res.weight: copying a param with shape torch.Size([4, 2, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 16, 1, 1]).
size mismatch for D.blocks.1.conv_res.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for D.blocks.1.net.0.weight: copying a param with shape torch.Size([4, 2, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 16, 3, 3]).
size mismatch for D.blocks.1.net.0.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for D.blocks.1.net.2.weight: copying a param with shape torch.Size([4, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]).
size mismatch for D.blocks.1.net.2.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for D.blocks.1.downsample.weight: copying a param with shape torch.Size([4, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]).
size mismatch for D.blocks.1.downsample.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for D.blocks.2.conv_res.weight: copying a param with shape torch.Size([8, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 32, 1, 1]).
size mismatch for D.blocks.2.conv_res.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for D.blocks.2.net.0.weight: copying a param with shape torch.Size([8, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 32, 3, 3]).
size mismatch for D.blocks.2.net.0.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for D.blocks.2.net.2.weight: copying a param with shape torch.Size([8, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for D.blocks.2.net.2.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for D.blocks.2.downsample.weight: copying a param with shape torch.Size([8, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for D.blocks.2.downsample.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for D.blocks.3.conv_res.weight: copying a param with shape torch.Size([16, 8, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 64, 1, 1]).
size mismatch for D.blocks.3.conv_res.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for D.blocks.3.net.0.weight: copying a param with shape torch.Size([16, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 64, 3, 3]).
size mismatch for D.blocks.3.net.0.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for D.blocks.3.net.2.weight: copying a param with shape torch.Size([16, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for D.blocks.3.net.2.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for D.blocks.3.downsample.weight: copying a param with shape torch.Size([16, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for D.blocks.3.downsample.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for D.blocks.4.conv_res.weight: copying a param with shape torch.Size([32, 16, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 128, 1, 1]).
size mismatch for D.blocks.4.conv_res.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for D.blocks.4.net.0.weight: copying a param with shape torch.Size([32, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 3, 3]).
size mismatch for D.blocks.4.net.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for D.blocks.4.net.2.weight: copying a param with shape torch.Size([32, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 256, 3, 3]).
size mismatch for D.blocks.4.net.2.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for D.blocks.4.downsample.weight: copying a param with shape torch.Size([32, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 256, 3, 3]).
size mismatch for D.blocks.4.downsample.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for D.blocks.5.conv_res.weight: copying a param with shape torch.Size([64, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 256, 1, 1]).
size mismatch for D.blocks.5.conv_res.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for D.blocks.5.net.0.weight: copying a param with shape torch.Size([64, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 256, 3, 3]).
size mismatch for D.blocks.5.net.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for D.blocks.5.net.2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 512, 3, 3]).
size mismatch for D.blocks.5.net.2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for D.blocks.5.downsample.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 512, 3, 3]).
size mismatch for D.blocks.5.downsample.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for D.blocks.6.conv_res.weight: copying a param with shape torch.Size([128, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 512, 1, 1]).
size mismatch for D.blocks.6.conv_res.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for D.blocks.6.net.0.weight: copying a param with shape torch.Size([128, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 512, 3, 3]).
size mismatch for D.blocks.6.net.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for D.blocks.6.net.2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for D.blocks.6.net.2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for D.to_logit.weight: copying a param with shape torch.Size([1, 2048]) from checkpoint, the shape in current model is torch.Size([1, 4096]).
size mismatch for GE.initial_block: copying a param with shape torch.Size([8, 4, 4]) from checkpoint, the shape in current model is torch.Size([64, 4, 4]).
size mismatch for GE.blocks.0.to_style1.weight: copying a param with shape torch.Size([8, 512]) from checkpoint, the shape in current model is torch.Size([64, 512]).
size mismatch for GE.blocks.0.to_style1.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for GE.blocks.0.to_noise1.weight: copying a param with shape torch.Size([512, 1]) from checkpoint, the shape in current model is torch.Size([1024, 1]).
size mismatch for GE.blocks.0.to_noise1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for GE.blocks.0.conv1.weight: copying a param with shape torch.Size([512, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 64, 3, 3]).
size mismatch for GE.blocks.0.to_style2.weight: copying a param with shape torch.Size([512, 512]) from checkpoint, the shape in current model is torch.Size([1024, 512]).
size mismatch for GE.blocks.0.to_style2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for GE.blocks.0.to_noise2.weight: copying a param with shape torch.Size([512, 1]) from checkpoint, the shape in current model is torch.Size([1024, 1]).
size mismatch for GE.blocks.0.to_noise2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for GE.blocks.0.conv2.weight: copying a param with shape torch.Size([512, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for GE.blocks.0.to_rgb.to_style.weight: copying a param with shape torch.Size([512, 512]) from checkpoint, the shape in current model is torch.Size([1024, 512]).
size mismatch for GE.blocks.0.to_rgb.to_style.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for GE.blocks.0.to_rgb.conv.weight: copying a param with shape torch.Size([3, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 1024, 1, 1]).
size mismatch for GE.blocks.1.to_style1.weight: copying a param with shape torch.Size([512, 512]) from checkpoint, the shape in current model is torch.Size([1024, 512]).
size mismatch for GE.blocks.1.to_style1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for GE.blocks.1.to_noise1.weight: copying a param with shape torch.Size([256, 1]) from checkpoint, the shape in current model is torch.Size([512, 1]).
size mismatch for GE.blocks.1.to_noise1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for GE.blocks.1.conv1.weight: copying a param with shape torch.Size([256, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 1024, 3, 3]).
size mismatch for GE.blocks.1.to_style2.weight: copying a param with shape torch.Size([256, 512]) from checkpoint, the shape in current model is torch.Size([512, 512]).
size mismatch for GE.blocks.1.to_style2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for GE.blocks.1.to_noise2.weight: copying a param with shape torch.Size([256, 1]) from checkpoint, the shape in current model is torch.Size([512, 1]).
size mismatch for GE.blocks.1.to_noise2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for GE.blocks.1.conv2.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 512, 3, 3]).
size mismatch for GE.blocks.1.to_rgb.to_style.weight: copying a param with shape torch.Size([256, 512]) from checkpoint, the shape in current model is torch.Size([512, 512]).
size mismatch for GE.blocks.1.to_rgb.to_style.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for GE.blocks.1.to_rgb.conv.weight: copying a param with shape torch.Size([3, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 512, 1, 1]).
size mismatch for GE.blocks.2.to_style1.weight: copying a param with shape torch.Size([256, 512]) from checkpoint, the shape in current model is torch.Size([512, 512]).
size mismatch for GE.blocks.2.to_style1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for GE.blocks.2.to_noise1.weight: copying a param with shape torch.Size([128, 1]) from checkpoint, the shape in current model is torch.Size([256, 1]).
size mismatch for GE.blocks.2.to_noise1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for GE.blocks.2.conv1.weight: copying a param with shape torch.Size([128, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 512, 3, 3]).
size mismatch for GE.blocks.2.to_style2.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for GE.blocks.2.to_style2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for GE.blocks.2.to_noise2.weight: copying a param with shape torch.Size([128, 1]) from checkpoint, the shape in current model is torch.Size([256, 1]).
size mismatch for GE.blocks.2.to_noise2.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for GE.blocks.2.conv2.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 256, 3, 3]).
size mismatch for GE.blocks.2.to_rgb.to_style.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for GE.blocks.2.to_rgb.to_style.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for GE.blocks.2.to_rgb.conv.weight: copying a param with shape torch.Size([3, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 256, 1, 1]).
size mismatch for GE.blocks.3.to_style1.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([256, 512]).
size mismatch for GE.blocks.3.to_style1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for GE.blocks.3.to_noise1.weight: copying a param with shape torch.Size([64, 1]) from checkpoint, the shape in current model is torch.Size([128, 1]).
size mismatch for GE.blocks.3.to_noise1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for GE.blocks.3.conv1.weight: copying a param with shape torch.Size([64, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 256, 3, 3]).
size mismatch for GE.blocks.3.to_style2.weight: copying a param with shape torch.Size([64, 512]) from checkpoint, the shape in current model is torch.Size([128, 512]).
size mismatch for GE.blocks.3.to_style2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for GE.blocks.3.to_noise2.weight: copying a param with shape torch.Size([64, 1]) from checkpoint, the shape in current model is torch.Size([128, 1]).
size mismatch for GE.blocks.3.to_noise2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for GE.blocks.3.conv2.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for GE.blocks.3.to_rgb.to_style.weight: copying a param with shape torch.Size([64, 512]) from checkpoint, the shape in current model is torch.Size([128, 512]).
size mismatch for GE.blocks.3.to_rgb.to_style.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for GE.blocks.3.to_rgb.conv.weight: copying a param with shape torch.Size([3, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 128, 1, 1]).
size mismatch for GE.blocks.4.to_style1.weight: copying a param with shape torch.Size([64, 512]) from checkpoint, the shape in current model is torch.Size([128, 512]).
size mismatch for GE.blocks.4.to_style1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for GE.blocks.4.to_noise1.weight: copying a param with shape torch.Size([32, 1]) from checkpoint, the shape in current model is torch.Size([64, 1]).
size mismatch for GE.blocks.4.to_noise1.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for GE.blocks.4.conv1.weight: copying a param with shape torch.Size([32, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 128, 3, 3]).
size mismatch for GE.blocks.4.to_style2.weight: copying a param with shape torch.Size([32, 512]) from checkpoint, the shape in current model is torch.Size([64, 512]).
size mismatch for GE.blocks.4.to_style2.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for GE.blocks.4.to_noise2.weight: copying a param with shape torch.Size([32, 1]) from checkpoint, the shape in current model is torch.Size([64, 1]).
size mismatch for GE.blocks.4.to_noise2.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for GE.blocks.4.conv2.weight: copying a param with shape torch.Size([32, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for GE.blocks.4.to_rgb.to_style.weight: copying a param with shape torch.Size([32, 512]) from checkpoint, the shape in current model is torch.Size([64, 512]).
size mismatch for GE.blocks.4.to_rgb.to_style.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for GE.blocks.4.to_rgb.conv.weight: copying a param with shape torch.Size([3, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 64, 1, 1]).
size mismatch for GE.blocks.5.to_style1.weight: copying a param with shape torch.Size([32, 512]) from checkpoint, the shape in current model is torch.Size([64, 512]).
size mismatch for GE.blocks.5.to_style1.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for GE.blocks.5.to_noise1.weight: copying a param with shape torch.Size([16, 1]) from checkpoint, the shape in current model is torch.Size([32, 1]).
size mismatch for GE.blocks.5.to_noise1.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for GE.blocks.5.conv1.weight: copying a param with shape torch.Size([16, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 64, 3, 3]).
size mismatch for GE.blocks.5.to_style2.weight: copying a param with shape torch.Size([16, 512]) from checkpoint, the shape in current model is torch.Size([32, 512]).
size mismatch for GE.blocks.5.to_style2.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for GE.blocks.5.to_noise2.weight: copying a param with shape torch.Size([16, 1]) from checkpoint, the shape in current model is torch.Size([32, 1]).
size mismatch for GE.blocks.5.to_noise2.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for GE.blocks.5.conv2.weight: copying a param with shape torch.Size([16, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([32, 32, 3, 3]).
size mismatch for GE.blocks.5.to_rgb.to_style.weight: copying a param with shape torch.Size([16, 512]) from checkpoint, the shape in current model is torch.Size([32, 512]).
size mismatch for GE.blocks.5.to_rgb.to_style.bias: copying a param with shape torch.Size([16]) from checkpoint, the shape in current model is torch.Size([32]).
size mismatch for GE.blocks.5.to_rgb.conv.weight: copying a param with shape torch.Size([3, 16, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 32, 1, 1]).
(SG_pytorch) alberto@spgroup-desktop:~/Documents/StyleGAN_reimplementations/stylegan2_lucidrains$ stylegan2_pytorch --generate
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment