failing to compute hair_mask with CDGnet about neuralhaircut

[kenshi84]

I encountered the same issue, and was able to fix it by modifying the code as

     state_dict = model.state_dict().copy()
     state_dict_old = torch.load(args.CDGNET_ckpt, map_location='cpu')
 
-    for key, nkey in zip(state_dict_old.keys(), state_dict.keys()):
+    state_dict_keys = list(state_dict.keys())
+    for key, nkey in zip(state_dict_old.keys(), state_dict_keys):
         if key != nkey:
             # remove the 'module.' in the 'key'
             state_dict[key[7:]] = deepcopy(state_dict_old[key])

and then downloading a different version of LIP_epoch_149.pth from this Google Drive link, posted in tjpulkl/CDGNet#5.

Hope this helps!

[op10ds]

Hi Kenshi,
yeah the checkpoint file you linked works well. The size is bigger than the one indicated by the authors, so that may be corrupted.
Thanks a lot.