# 'val accuracy': [observables.logs['val_accuracy']],
# 'val vr': [observables.logs['val_uncertainty_vr']],
# 'val pe': [observables.logs['val_uncertainty_pe']],
# 'val mi': [observables.logs['val_uncertainty_mi']],
'risk': [risks],
'delta': [delta],
'eval accuracy vr': [eval_acc_vrs],
'eval accuracy pe': [eval_acc_pes],
'eval accuracy mi': [eval_acc_mis],
'eval coverage vr': [eval_coverage_vrs],
'eval coverage pe': [eval_coverage_pes],
'eval coverage mi': [eval_coverage_mis],
'seen uncertainty vr': [eval_vr],
'seen uncertainty pe': [eval_pe],
'seen uncertainty mi': [eval_mi],
'threshold vr': [thresholds_vr],
'threshold pe': [thresholds_pe],
'threshold mi': [thresholds_mi],
'true labels': [true_eval_labels],
'eval preds': [eval_preds],
})
convert_df_to_cpu(res)
save_to_file(loss, './output/loss.pkl')
save_to_file(observables, './output/TrainingLogs.pkl')
torch.save(all_outputs_eval, './output/softmax_outputs.pt')
# torch.save(res, './output/results.pt')
res.to_pickle('./output/results.pkl')
torch.save(bay_net.state_dict(), './output/final_weights.pt')
f'Mutual Information:{unseen_mi.mean()}')
res = pd.concat((res,
pd.DataFrame.from_dict({
'sigma_initial': [log(1 + exp(rho))],
'seen_uncertainty_vr': [eval_vr],
'seen_uncertainty_pe': [eval_pe],
'seen_uncertainty_mi': [eval_mi],
'unseen_uncertainty_vr': [unseen_vr],
'unseen_uncertainty_pe': [unseen_pe],
'unseen_uncertainty_mi': [unseen_mi],
})),
axis=1)
convert_df_to_cpu(res)
save_to_file(arguments, f'{output_file}/arguments.pkl')
if args.save_loss:
save_to_file(loss, f'{output_file}/loss.pkl')
if args.save_observables:
save_to_file(observables, f'{output_file}/TrainingLogs.pkl')
if args.save_outputs:
torch.save(all_outputs_unseen, f'{output_file}/unseen_outputs.pt')
torch.save(all_outputs_eval, f'{output_file}/seen_outputs.pt')
# torch.save(res, f'{output_file}/results.pt')
res.to_pickle(f'{output_file}/results.pkl')
torch.save(bay_net.state_dict(), f'{output_file}/final_weights.pt')
torch.save(observables.max_weights, f'{output_file}/best_weights.pt')
pd.DataFrame.from_dict({k: [v]
for k, v in arguments.items()
}).to_csv(f'{output_file}/arguments.csv')