A07: Indoor Scene Recognition


  1. Build an accurate model for the indoor scenes dataset (from here). Achieve at least 60% accuracy on the test files. Use the files (as split into train/validation/test) from delenn: /bigdata/data/indoor-scenes/
  2. Save the model to a file (as simple as model.save(fname)), and write a separate program that loads the model and predicts the scene for a given image provided by the user. Note, you’ll have to resize the image to fit the model’s expectations. Show the top three predictions & probabilities.


CSCI 431 material by Joshua Eckroth is licensed under a Creative Commons Attribution-ShareAlike 3.0 Unported License. Source code for this website available at GitHub.