Project 1 - Image prediction

Due date: Oct 8 2018, 1:00am


This project focuses on image level prediction using deep (convolutional) networks. In this project you will train a network to predict a single label from an image. You have two choices for datasets: Age prediction from yearbook photos or geolocation prediction from streetview images.


Face to age


test file


This dataset contains frontal-facing American high school year-book photos with labels to indicate the years those photos were taken. Your task is to train a deep network to predict the year a novel image was taken.

Dataset credit Shiry Ginosar



test file


This dataset contains images from France street view with geolocation label (latitude and longitude). You task is to predict the geolocation of novel street view images.

Dataset credit Carl Doersch

Starter code and data

Check the starter code out here.

For both project, we provide you with a training data set and a validation data set (you can use it as your test set). However, we will keep a hidden test set to make sure your algorithm is not overfitting too much.

We also provide you with a python script named which defines the interface we will use to evaluate your code on the test set. You can modify to run your own model (including loading your parameters). See the comment in script to know how we will test your code. Make sure your works with the evaluation code we provide without any modifications to the evaluation code. Otherwise we will not be able to evaluate your code and you might not get the full credit.

The starter code also contains scripts to load the images and labels for your convenience.


  1. A writeup. Preferably in latex using the CVPR 2018 stylesheet. It should contain:
    • An intro and abstract outlining the method you chose and why it’s better than alternatives.
    • A technical section, with a detailed overview of your method and any extensions.
    • A thorough evaluation of any aspects of your method. Try to justify every choice you made either with a sound argument plus citation or with an experiment.
  2. The code and parameters to run your model. This code should be written in python. Contact the TA if not.

How to submit

Please submit a pdf of your writeup, your results on the test set and your code in a single compressed file named as [UTEID]_[You name]_[yearbook/geo].[zip/rar/tar.gz] (e.g. pk0000_PhilippKraehenbuehl_yearbook.tar.gz) The yearbook and geo mean which project you choose. If you decide to try both please submit two files (with the same writeup file). The compressed files should include:

  1. modified you can add anything, just to make sure the TA can get predicted label by calling predict(image_path) in class Predictor.
  2. A report named report.pdf, as detailed above.
  3. Any dependencies you used that the (e.g. trained model file, other auxiliary python files)
  4. A text file with the results on the test set.
  5. Put Model and generated test label file in the respective folder.
  6. Add file in your submission with proper description of each files.
  7. Project should be run from the file as shown in the evaluation step and should be able to generate the test label file. Make sure while generating test label file, do not shuffle the data.
  8. There should not be any mismatch between the test label file and the label predict by the model. Otherwise, your entry will be rejected.

Additional notes:


Each team has 7 min to present. Not every team member needs to speak, if you don’t want. A good presentation should spend:


This project counts 25% towards your final grade. The 25 points are split up as follows:

If you get more than 25pt we truncate the project 1 score at 25% (including presentation).

Late submission policy

The presentation cannot be late, you will loose 10pt if you do not have a presentation ready. You will lose 2pt for every day the submission is late. You will also not be eligible for the best submission score.