RuntimeError: Error(s) in loading state_dict for DataParallel

[kongsa0419]

First of all, Thank you for your effort of this great work.

I was following the documentation. while this part, [https://github.com/clovaai/stargan-v2#generating-interpolation-videos]

I got an Erorr "RuntimeError: Error(s) in loading state_dict for DataParallel" (*Attached entire error statements below)

Now I know that the 'module.' prefix matters, because of the torch.nn.DataParallel, but I'm confused how to solve that error.

Would anyone suggest me the code? (* I already saw #103 )

---

Namespace(batch_size=8, beta1=0.0, beta2=0.99, checkpoint_dir='expr/checkpoints/celeba_hq', ds_iter=100000, eval_dir='expr/eval', eval_every=50000, f_lr=1e-06, hidden_dim=512, img_size=256, inp_dir='assets/representative/custom/female', lambda_cyc=1, lambda_ds=1, lambda_reg=1, lambda_sty=1, latent_dim=16, lm_path='expr/checkpoints/celeba_lm_mean.npz', lr=0.0001, mode='sample', num_domains=2, num_outs_per_domain=10, num_workers=4, out_dir='assets/representative/celeba_hq/src/female', print_every=10, randcrop_prob=0.5, ref_dir='assets/representative/celeba_hq/ref', result_dir='expr/results/celeba_hq', resume_iter=100000, sample_dir='expr/samples', sample_every=5000, save_every=10000, seed=777, src_dir='assets/representative/celeba_hq/src', style_dim=64, total_iters=100000, train_img_dir='data/celeba_hq/train', val_batch_size=32, val_img_dir='data/celeba_hq/val', w_hpf=1.0, weight_decay=0.0001, wing_path='expr/checkpoints/wing.ckpt') Number of parameters of generator: 43467395 Number of parameters of mapping_network: 2438272 Number of parameters of style_encoder: 20916928 Number of parameters of discriminator: 20852290 Number of parameters of fan: 6333603 Initializing generator... Initializing mapping_network... Initializing style_encoder... Initializing discriminator... Preparing DataLoader for the generation phase... Preparing DataLoader for the generation phase... Loading checkpoint from expr/checkpoints/celeba_hq\100000_nets_ema.ckpt... Traceback (most recent call last): File "main.py", line 182, in main(args) File "main.py", line 73, in main solver.sample(loaders) File "C:\Users\Admin\anaconda3\envs\stargan-v2\lib\site-packages\torch\autograd\grad_mode.py", line 28, in decorate_context return func(*args, **kwargs) File "C:\stargan-v2\core\solver.py", line 178, in sample self._load_checkpoint(args.resume_iter) File "C:\stargan-v2\core\solver.py", line 73, in _load_checkpoint ckptio.load(step) File "C:\stargan-v2\core\checkpoint.py", line 50, in load module.load_state_dict(module_dict[name]) File "C:\Users\Admin\anaconda3\envs\stargan-v2\lib\site-packages\torch\nn\modules\module.py", line 1483, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for DataParallel: Missing key(s) in state_dict: "module.from_rgb.weight", "module.from_rgb.bias", "module.encode.0.conv1.weight", "module.encode.0.conv1.bias", "module.encode.0.conv2.weight", "module.encode.0.conv2.bias", "module.encode.0.norm1.weight", "module.encode.0.norm1.bias", "module.encode.0.norm2.weight", "module.encode.0.norm2.bias", "module.encode.0.conv1x1.weight", "module.encode.1.conv1.weight", "module.encode.1.conv1.bias", "module.encode.1.conv2.weight", "module.encode.1.conv2.bias", "module.encode.1.norm1.weight", "module.encode.1.norm1.bias", "module.encode.1.norm2.weight", "module.encode.1.norm2.bias", "module.encode.1.conv1x1.weight", "module.encode.2.conv1.weight", "module.encode.2.conv1.bias", "module.encode.2.conv2.weight", "module.encode.2.conv2.bias", "module.encode.2.norm1.weight", "module.encode.2.norm1.bias", "module.encode.2.norm2.weight", "module.encode.2.norm2.bias", "module.encode.2.conv1x1.weight", "module.encode.3.conv1.weight", "module.encode.3.conv1.bias", "module.encode.3.conv2.weight", "module.encode.3.conv2.bias", "module.encode.3.norm1.weight", "module.encode.3.norm1.bias", "module.encode.3.norm2.weight", "module.encode.3.norm2.bias", "module.encode.4.conv1.weight", "module.encode.4.conv1.bias", "module.encode.4.conv2.weight", "module.encode.4.conv2.bias", "module.encode.4.norm1.weight", "module.encode.4.norm1.bias", "module.encode.4.norm2.weight", "module.encode.4.norm2.bias", "module.encode.5.conv1.weight", "module.encode.5.conv1.bias", "module.encode.5.conv2.weight", "module.encode.5.conv2.bias", "module.encode.5.norm1.weight", "module.encode.5.norm1.bias", "module.encode.5.norm2.weight", "module.encode.5.norm2.bias", "module.encode.6.conv1.weight", "module.encode.6.conv1.bias", "module.encode.6.conv2.weight", "module.encode.6.conv2.bias", "module.encode.6.norm1.weight", "module.encode.6.norm1.bias", "module.encode.6.norm2.weight", "module.encode.6.norm2.bias", "module.decode.0.conv1.weight", "module.decode.0.conv1.bias", "module.decode.0.conv2.weight", "module.decode.0.conv2.bias", "module.decode.0.norm1.fc.weight", "module.decode.0.norm1.fc.bias", "module.decode.0.norm2.fc.weight", "module.decode.0.norm2.fc.bias", "module.decode.1.conv1.weight", "module.decode.1.conv1.bias", "module.decode.1.conv2.weight", "module.decode.1.conv2.bias", "module.decode.1.norm1.fc.weight", "module.decode.1.norm1.fc.bias", "module.decode.1.norm2.fc.weight", "module.decode.1.norm2.fc.bias", "module.decode.2.conv1.weight", "module.decode.2.conv1.bias", "module.decode.2.conv2.weight", "module.decode.2.conv2.bias", "module.decode.2.norm1.fc.weight", "module.decode.2.norm1.fc.bias", "module.decode.2.norm2.fc.weight", "module.decode.2.norm2.fc.bias", "module.decode.3.conv1.weight", "module.decode.3.conv1.bias", "module.decode.3.conv2.weight", "module.decode.3.conv2.bias", "module.decode.3.norm1.fc.weight", "module.decode.3.norm1.fc.bias", "module.decode.3.norm2.fc.weight", "module.decode.3.norm2.fc.bias", "module.decode.4.conv1.weight", "module.decode.4.conv1.bias", "module.decode.4.conv2.weight", "module.decode.4.conv2.bias", "module.decode.4.norm1.fc.weight", "module.decode.4.norm1.fc.bias", "module.decode.4.norm2.fc.weight", "module.decode.4.norm2.fc.bias", "module.decode.4.conv1x1.weight", "module.decode.5.conv1.weight", "module.decode.5.conv1.bias", "module.decode.5.conv2.weight", "module.decode.5.conv2.bias", "module.decode.5.norm1.fc.weight", "module.decode.5.norm1.fc.bias", "module.decode.5.norm2.fc.weight", "module.decode.5.norm2.fc.bias", "module.decode.5.conv1x1.weight", "module.decode.6.conv1.weight", "module.decode.6.conv1.bias", "module.decode.6.conv2.weight", "module.decode.6.conv2.bias", "module.decode.6.norm1.fc.weight", "module.decode.6.norm1.fc.bias", "module.decode.6.norm2.fc.weight", "module.decode.6.norm2.fc.bias", "module.decode.6.conv1x1.weight", "module.to_rgb.0.weight", "module.to_rgb.0.bias", "module.to_rgb.2.weight", "module.to_rgb.2.bias", "module.hpf.filter". Unexpected key(s) in state_dict: "from_rgb.weight", "from_rgb.bias", "encode.0.conv1.weight", "encode.0.conv1.bias", "encode.0.conv2.weight", "encode.0.conv2.bias", "encode.0.norm1.weight", "encode.0.norm1.bias", "encode.0.norm2.weight", "encode.0.norm2.bias", "encode.0.conv1x1.weight", "encode.1.conv1.weight", "encode.1.conv1.bias", "encode.1.conv2.weight", "encode.1.conv2.bias", "encode.1.norm1.weight", "encode.1.norm1.bias", "encode.1.norm2.weight", "encode.1.norm2.bias", "encode.1.conv1x1.weight", "encode.2.conv1.weight", "encode.2.conv1.bias", "encode.2.conv2.weight", "encode.2.conv2.bias", "encode.2.norm1.weight", "encode.2.norm1.bias", "encode.2.norm2.weight", "encode.2.norm2.bias", "encode.2.conv1x1.weight", "encode.3.conv1.weight", "encode.3.conv1.bias", "encode.3.conv2.weight", "encode.3.conv2.bias", "encode.3.norm1.weight", "encode.3.norm1.bias", "encode.3.norm2.weight", "encode.3.norm2.bias", "encode.4.conv1.weight", "encode.4.conv1.bias", "encode.4.conv2.weight", "encode.4.conv2.bias", "encode.4.norm1.weight", "encode.4.norm1.bias", "encode.4.norm2.weight", "encode.4.norm2.bias", "encode.5.conv1.weight", "encode.5.conv1.bias", "encode.5.conv2.weight", "encode.5.conv2.bias", "encode.5.norm1.weight", "encode.5.norm1.bias", "encode.5.norm2.weight", "encode.5.norm2.bias", "encode.6.conv1.weight", "encode.6.conv1.bias", "encode.6.conv2.weight", "encode.6.conv2.bias", "encode.6.norm1.weight", "encode.6.norm1.bias", "encode.6.norm2.weight", "encode.6.norm2.bias", "decode.0.conv1.weight", "decode.0.conv1.bias", "decode.0.conv2.weight", "decode.0.conv2.bias", "decode.0.norm1.fc.weight", "decode.0.norm1.fc.bias", "decode.0.norm2.fc.weight", "decode.0.norm2.fc.bias", "decode.1.conv1.weight", "decode.1.conv1.bias", "decode.1.conv2.weight", "decode.1.conv2.bias", "decode.1.norm1.fc.weight", "decode.1.norm1.fc.bias", "decode.1.norm2.fc.weight", "decode.1.norm2.fc.bias", "decode.2.conv1.weight", "decode.2.conv1.bias", "decode.2.conv2.weight", "decode.2.conv2.bias", "decode.2.norm1.fc.weight", "decode.2.norm1.fc.bias", "decode.2.norm2.fc.weight", "decode.2.norm2.fc.bias", "decode.3.conv1.weight", "decode.3.conv1.bias", "decode.3.conv2.weight", "decode.3.conv2.bias", "decode.3.norm1.fc.weight", "decode.3.norm1.fc.bias", "decode.3.norm2.fc.weight", "decode.3.norm2.fc.bias", "decode.4.conv1.weight", "decode.4.conv1.bias", "decode.4.conv2.weight", "decode.4.conv2.bias", "decode.4.norm1.fc.weight", "decode.4.norm1.fc.bias", "decode.4.norm2.fc.weight", "decode.4.norm2.fc.bias", "decode.4.conv1x1.weight", "decode.5.conv1.weight", "decode.5.conv1.bias", "decode.5.conv2.weight", "decode.5.conv2.bias", "decode.5.norm1.fc.weight", "decode.5.norm1.fc.bias", "decode.5.norm2.fc.weight", "decode.5.norm2.fc.bias", "decode.5.conv1x1.weight", "decode.6.conv1.weight", "decode.6.conv1.bias", "decode.6.conv2.weight", "decode.6.conv2.bias", "decode.6.norm1.fc.weight", "decode.6.norm1.fc.bias", "decode.6.norm2.fc.weight", "decode.6.norm2.fc.bias", "decode.6.conv1x1.weight", "to_rgb.0.weight", "to_rgb.0.bias", "to_rgb.2.weight", "to_rgb.2.bias".