Does anyone know how to input text data (not imdb data, my own text data) into the model from lesson 4 https://github.com/fastai/fastai/blob/master/courses/dl1/lesson4-imdb.ipynb ? I want to input some text data that I have into the model and find out whether they are positive or negative. I have done every step in lesson 4 but got stuck at this last step.
You can call learn.predict(text) with text being what you want to test the model on. The learner should return the label (pos/neg), the class_id (0/1) and the softmax probabilities.
Thank you so much for your reply! My file is currently in a csv format. Do you know how I can load it into the right format so that the learn.predict function will work?
Hi,
I too have the same problem…
I was able to create a Language Model and was able to predict sentences, i have a CSV file which has 3 columns Text is in the 2nd column and my Label is in the 3rd column. When i am trying to build a classifier using the Language Model i built, i am not able to build a data bunch from my CSV file similar to IMDB classifier from folder which was discussed in today’s class. Can some one help me on this.