Thanks, this is the missing step:
What is m3
here? I opened a ticket (incorrectly, should have just come here to the forums) to ask about how to predict individual strings within the IMDB tutorial (https://github.com/fastai/fastai/issues/873), but there doesn’t seem to be a variable m3
in the notebook (at least not any more?). How do we best get the model object out of the learn
object as shown in this notebook: https://github.com/fastai/fastai/blob/master/examples/text.ipynb ?
It is a model defined here: How to interpret IMDB sentiment predictions?. I believe it comes from the IMDb notebook originally though.
m3 = md2.get_model(opt_fn, 1500, bptt, emb_sz=em_sz, n_hid=nh, n_layers=nl,
dropouti=dropouti, dropout=dropout, wdrop=wdrop,
dropoute=dropoute, dropouth=dropouth)
1 Like