Hi, thanks for the response. This is my error message:
RuntimeError: Error(s) in loading state_dict for Generator: Missing key(s) in state_dict:
"main.0.weight", "main.1.weight", "main.1.bias", "main.1.running_mean", "main.1.running_var",
"main.3.weight", "main.4.weight", "main.4.bias", "main.4.running_mean", "main.4.running_var",
"main.6.weight", "main.7.weight", "main.7.bias", "main.7.running_mean", "main.7.running_var",
"main.9.weight", "main.10.weight", "main.10.bias", "main.10.running_mean", "main.10.running_var",
"main.12.weight".
Unexpected key(s) in state_dict: "module.main.0.weight", "module.main.1.weight",
"module.main.1.bias", "module.main.1.running_mean", "module.main.1.running_var",
"module.main.1.num_batches_tracked", "module.main.3.weight", "module.main.4.weight",
"module.main.4.bias", "module.main.4.running_mean", "module.main.4.running_var",
"module.main.4.num_batches_tracked", "module.main.6.weight", "module.main.7.weight",
"module.main.7.bias", "module.main.7.running_mean", "module.main.7.running_var",
"module.main.7.num_batches_tracked", "module.main.9.weight", "module.main.10.weight",
"module.main.10.bias", "module.main.10.running_mean", "module.main.10.running_var",
"module.main.10.num_batches_tracked", "module.main.12.weight".
I think the scheduler is causing my outputs to be meaningless because I had run the same training previously without the scheduler and didn’t have this error when loading the saved model and my outputs were what I would expect. I looked up a different thread on this forum by someone who had the same error and the suggested solution was to use strict = False
to fix this error. But as you said, I think this argument is causing issues.
Alternatively, I am not sure how to account for missing weights when I load my trained model.