I am looking for ways to combine multiple inputs including numerical data, categorical data and image data for training a model. Numerical and categorical data include features like:
- Number of bedrooms
- Number of bathrooms
- Area (i.e., square footage)
- Zip code
Images are of four different sections of a house like the following:
Refer here for more on the dataset. The image example shown above is also a montage which does not come by default.
The aim is to combine this image data and the other numerical and categorical data mentioned above and train a model to predict house price. Any direction to for preparing a fastai compatible data for this purpose would be highly helpful.