D.A. Forsyth --- 3310 Siebel Center

Trevor Walker --- 4207 Siebel Center

Office Hours Time: TBA, Location: TBA

You may do this homework in groups of up to three

Submission: Submission process to be announced

You may do this homework in groups of up to 3 contributors. Groups of 1 or of 2 are just fine, too.

Variational autoencoders: We will evaluate variational autoencoders applied to the MNIST dataset.

Obtain (or write! but this isn't required) a tensorflow code for a variational autoencoder. Train this autoencoder on the MNIST dataset. Use only the MNIST training set.
We now need to determine how well the codes produced by this autoencoder can be interpolated.
- For 10 pairs of MNIST test images of the same digit, selected at random, compute the code for each image of the pair. Now compute 7 evenly spaced linear interpolates between these codes, and decode the result into images. Prepare a figure showing this interpolate. Lay out the figure so each interpolate is a row. On the left of the row is the first test image; then the interpolate closest to it; etc; to the last test image. You should have a 10 rows and 9 columns of images.
- For 10 pairs of MNIST test images of different digits, selected at random, compute the code for each image of the pair. Now compute 7 evenly spaced linear interpolates between these codes, and decode the result into images. Prepare a figure showing this interpolate. Lay out the figure so each interpolate is a row. On the left of the row is the first test image; then the interpolate closest to it; etc; to the last test image. You should have a 10 rows and 9 columns of images.