Usign ULMFiT for inference

[Samuel]

Please see

Can't replicate ULMFit validation predictions

I’ve been trying to do (true/false) classification with ULMFit and I’ve had some trouble working out how to predict on just normal text (not loaded from a dataset). Or rather - I can get it to do something, but the predictions seem wrong. So I thought I’d take the first row of the validation set and try to get it to predict the same result manually. Here’s what I’m aiming for: preds = learn.predict() preds[0] array([ 0.88123, -0.47445], dtype=float32) Here’s my code: # get the first row of…

ULMFit: understanding learner.predict

I am using ULMfit for a regression task. After finetuning, and training the classifier, I want to make predictions on new data (that has been preprocessed the same way as the training data.) I am trying to figure out which function to use: I see: learn.predict, learn.predict_array, learn.predict_dl, learn.predict_with_targs. Seems like most of these works with the dataset used to init RNN_Learner(). However, the size of the predicted array (from learn.predict) is larger than the size of the …