Export Tabular model

[shay1309 (shaythuram)]

Unable to visualize embedding distances

I had the same issue when trying to produce the PCA Matrix but for the fastai.collab model rather than the “create your own” DotProductBias based module. That class has the attribute “movie_factors” which our fastai.collab learn object doesn’t have: self.movie_factors = create_params([n_movies, n_factors]) I found a clue to the solution a little further down in the Embedding Distance section of the 2022 course (Lecture 8), which shows that our movie_factors is just: movie_factors = learn.mod…

Understanding Embeddings

[Screenshot 2020-12-28 at 8.56.08 PM] Trying to understand how embedding works, could someone explain : movies = self.movie_factors(x[:,1]) so we access the user factors and index to the movie_ID which is x then why do we do :,1 ? what do we do :,1 shouldn’t it just be movie_factors(x)? as such i decided to have a look at what the embedding looks like(by destructuring) but as shown in the image, I wasn’t able to do that.

Hi Sir, Above are the 2 questions. Also yep I get what you mean, lazy transforms is done “on the fly” so to speak … correct me if I’m wrong