Not getting predictions for NLP model get_preds

[sahil1234 (Sahil)]

Here are some answers which did not work for me

Fastbook Chapter 12 - Getting Predictions

Hi, had the same issue. After looking in to the predict functions/options it worked for me by manually generating a test dataset using the following specs: # Let's assume our model receives input 0, and the target is 1 random_sample = (tensor([0]), tensor([1])) # We need x number of samples (should be a multiple of the batch size you specified in the learner object, in the Notebook they suggest 64) # Let us just replicate the random_sample tensor test_data = [random_sample]*bs # Use ge…

@muellerzr had some answers to this in

Learn.get_preds() memory inefficiency - quick fix

Hey @hushitz! Thank you for such a detailed analysis! I’m going to work on this over the weekend will report back with what I did So here was my fix for Interpretation: preds, targs, decoded, losses = learn.get_preds(dl=dl, with_loss=True, with_decoded=True, act=None) l, idxs = losses.topk(5, largest=True) items = dl.dataset[idxs] o = dl.new(items, bs=len(items)) a, _ = o.one_batch() x,y,its = o._pre_show_batch(o.one_batch()) b_out = L(a) + L(decoded) x1,y1,outs = o._pre_show_ba…