[ICCVW 2019] PyTorch implementation of DSGAN and ESRGAN-FS from the paper "Frequency Separation for Real-World Super-Resolution". This code was the winning solution of the AIM challenge on Real-World Super-Resolution at ICCV 2019
MIT License
162
stars
37
forks
source link
_pickle.PicklingError: Can't pickle <function <lambda> at 0x7f308810e2f0>: attribute lookup <lambda> on __main__ failed #15
_pickle.PicklingError: Can't pickle <function at 0x7f308810e2f0>: attribute lookup on main failed
the scheduler_g.state_dict() is not right for 'torch.save(state_dict, path)'
state_dict = {
'epoch': epoch,
'iteration': iteration,
'model_g_state_dict': model_g.state_dict(),
'models_d_state_dict': model_d.state_dict(),
'optimizer_g_state_dict': optimizer_g.state_dict(),
'optimizer_d_state_dict': optimizer_d.state_dict(),
'scheduler_g_state_dict': scheduler_g.state_dict(),
'scheduler_d_state_dict': scheduler_d.state_dict(),
}
_pickle.PicklingError: Can't pickle <function at 0x7f308810e2f0>: attribute lookup on main failed
the scheduler_g.state_dict() is not right for 'torch.save(state_dict, path)'
state_dict = {
'epoch': epoch,
'iteration': iteration,
'model_g_state_dict': model_g.state_dict(),
'models_d_state_dict': model_d.state_dict(),
'optimizer_g_state_dict': optimizer_g.state_dict(),
'optimizer_d_state_dict': optimizer_d.state_dict(),
'scheduler_g_state_dict': scheduler_g.state_dict(),
'scheduler_d_state_dict': scheduler_d.state_dict(),
}