Code sample for multi-input with batches / fit_generator()?

This is going to be very common use case where deep learning classification task can be greatly improved by providing extra meta context, such as person’s age, or image location, or user’s IP address - in addition to main data, such as image or user session activity or tweet.

While we touched multi-input at Lesson 7 and Keras has couple of (incomplete) basic examples of multi-input - I couldn’t find anywhere a complete, simple, working piece of code leveraging model.fit_generator() where input comes in batches.

Anyone can help in that?

Gleb

In what way is the lesson 7 example incomplete?

I think it loads everything in memory and does not use flow_from_directory or batch iterators?

We’ll see today how to avoid this :slight_smile:

1 Like

Yay, highly appreciate, thank you Jeremy!
It took me few hours on sunday to search for solution - looking forward to tonight’s lesson.

Gleb