Test Trained Model

[Reham-Osama]

Is there a way to test the trained model without performing the training again and evaluating the model?

I used the following command for training:
python main.py -config config/mhqg-wq/graph2seq.yml

Now I need to use this trained model to do some predictions on a new file, Is there a way to do that given the current code?

[hugochan]

@Reham-Osama sorry for the late response! Yes, you can achieve the goal by commenting out model.train() in the main file.