The most straightforward way I’m familiar with for scoring a new dataframe is creating a test_dl, which runs through the procs, and then passing to
dl = learner.dls.test_dl(df, device="cuda") preds = learner.get_preds(dl=dl).numpy()
However, when working with large pandas dataframes, ram can end up being a bottle neck. I realized that learner.dls.test_dl() doesn’t allow passing
inplace=True to the new dataset, which ends up making a new copy.
Is there another straightforward way of processing and scoring a dataframe that doesn’t make a copy?