Demo code for reconstructed images from fine-tuned autoencoders
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.

CVPR 2018: What do deep Networks like to See?

Implementation from the CVPR 2018 paper "What do Deep Networks Like to See?".

This is a simple proof of concept that uses a fine-tuned autoencoder on ResNet50 to reconstruct input images.

  1. Download the Torch model from here and store it with the root directory of the repo.
  2. Call
python -i PATH

where PATH is the path to the input image. 3. An output image should be saved in the root directory of the repo with the reconstruction.


Original input and its reconstruction using an autoencoder fine-tuned on ResNet 50

For more info, please check out the paper's website.