Testing a trained model with other data

[teoaivalis]

I have trained ithemal over multiple Intel architectures with BHive dataset and now I want to test them with other data(over 100.000).
Is there any way to do it in a row?

The only way i found is with predict.py BUT I have to make all the time a.out files.
(python learning/pytorch/ithemal/predict.py --verbose --model predictor.dump --model-data trained.mdl --file a.out)

Have somebody developed any converted form of this code to run the tests in a row??

Thanks.