search

lucidrains / lightweight-gan

Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two
MIT License
1.63k stars 222 forks source link

Why Loop Train error??? #97

Open davidzj0718 opened 3 years ago

davidzj0718 commented 3 years ago

Run command:

!lightweight_gan --data='/content/my_data/1024' --image-size=1024 --batch-size=16 --gradient-accumulate-every=4 --network-capacity=16 --num-train-steps=200000 --results_dir='/content/drive/MyDrive/light-result' --models_dir='/content/drive/MyDrive/light-model'

Run Error info:

continuing from previous epoch - 58 loading from version 0.20.3 unable to load save model. please try downgrading the package to the version specified by the saved model Traceback (most recent call last): File "/usr/local/bin/lightweight_gan", line 8, in sys.exit(main()) File "/usr/local/lib/python3.7/dist-packages/lightweight_gan/cli.py", line 190, in main fire.Fire(train_from_folder) File "/usr/local/lib/python3.7/dist-packages/fire/core.py", line 141, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/usr/local/lib/python3.7/dist-packages/fire/core.py", line 471, in _Fire target=component.name) File "/usr/local/lib/python3.7/dist-packages/fire/core.py", line 681, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "/usr/local/lib/python3.7/dist-packages/lightweight_gan/cli.py", line 181, in train_from_folder run_training(0, 1, model_args, data, load_from, new, num_train_steps, name, seed) File "/usr/local/lib/python3.7/dist-packages/lightweight_gan/cli.py", line 59, in run_training model.load(load_from) File "/usr/local/lib/python3.7/dist-packages/lightweight_gan/lightweight_gan.py", line 1471, in load raise e File "/usr/local/lib/python3.7/dist-packages/lightweight_gan/lightweight_gan.py", line 1468, in load self.GAN.load_state_dict(load_data['GAN']) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1407, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for LightweightGAN: Missing key(s) in state_dict: "G.layers.3.2.norm.g", "G.layers.3.2.norm.b", "D.residual_layers.3.1.norm.g", "D.residual_layers.3.1.norm.b", "D.to_shape_disc_out.1.fn.norm.g", "D.to_shape_disc_out.1.fn.norm.b", "D.to_shape_disc_out.3.fn.norm.g", "D.to_shape_disc_out.3.fn.norm.b", "GE.layers.3.2.norm.g", "GE.layers.3.2.norm.b", "D_aug.D.residual_layers.3.1.norm.g", "D_aug.D.residual_layers.3.1.norm.b", "D_aug.D.to_shape_disc_out.1.fn.norm.g", "D_aug.D.to_shape_disc_out.1.fn.norm.b", "D_aug.D.to_shape_disc_out.3.fn.norm.g", "D_aug.D.to_shape_disc_out.3.fn.norm.b". Unexpected key(s) in state_dict: "G.layers.3.2.norm.weight", "G.layers.3.2.norm.bias", "D.residual_layers.3.1.norm.weight", "D.residual_layers.3.1.norm.bias", "D.to_shape_disc_out.1.fn.norm.weight", "D.to_shape_disc_out.1.fn.norm.bias", "D.to_shape_disc_out.3.fn.norm.weight", "D.to_shape_disc_out.3.fn.norm.bias", "GE.layers.3.2.norm.weight", "GE.layers.3.2.norm.bias", "D_aug.D.residual_layers.3.1.norm.weight", "D_aug.D.residual_layers.3.1.norm.bias", "D_aug.D.to_shape_disc_out.1.fn.norm.weight", "D_aug.D.to_shape_disc_out.1.fn.norm.bias", "D_aug.D.to_shape_disc_out.3.fn.norm.weight", "D_aug.D.to_shape_disc_out.3.fn.norm.bias".

davidzj0718 commented 3 years ago

continuing from previous epoch - 58.

davidzj0718 commented 3 years ago

continuing from previous epoch - 58. OK