Values after each epoch not getting stored

1

The code below calculates the MSE and MAE values but I have an issue where the values for MAE and MSE don’t get stored at each epoch in store_MAE and store MSE. It seems to use the values of the last epoch only. Any idea what i need to do in the code to save the total values for each epoch i hope this make since

       # logging:
        loss = torch.mean((preds - targets)**2)
        count_error = torch.abs(preds - targets).mean()
        mean_test_error += count_error
        writer.add_scalar('test_loss', loss.item(), global_step=global_step)
        writer.add_scalar('test_count_error', count_error.item(), global_step=global_step)
        
        global_step += 1
        store_MAE = 0
        store_MSE = 0
        mean_test_error = mean_test_error / len(loader_test)
        store_MAE += mean_test_error
        mse = math.sqrt(loss / len(loader_test))
        store_MSE +=mse
        print("Test count error: %f" % mean_test_error)
        print("MSE: %f" % mse)

    if mean_test_error < best_test_error:
        best_test_error = mean_test_error
        torch.save({'state_dict':model.state_dict(),
                    'optimizer_state_dict':optimizer.state_dict(),
                    'globalStep':global_step,
                    'train_paths':dataset_train.files,
                    'test_paths':dataset_test.files},checkpoint_path)

print("MAE Total: %f" % store_MAE)
print("MSE Total: %f" % store_MSE)
model_mae= store_MAE /epoch
model_mse= store_MSE /epoch
print("Model MAE: %f" % model_mae)
print("Model MSE: %f" % model_mse)
2

It seems you are reinitializing store_MAE and store_MSE inside the logging loop?
Could you move this code

        store_MAE = 0
        store_MSE = 0

before executing the loop?

1 Like
3

Many Thanks for your help!