Tensorflow implementation of "Deep Visual Analogy-Making"
Python Shell
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
assets update loss diagram Feb 14, 2016
model
.gitignore change optim, update sprite, edit loader Feb 12, 2016
LICENSE add LICENSE Aug 10, 2016
README.md update loss diagram Feb 14, 2016
download.sh loader in progress Feb 10, 2016
loader.py change optim, update sprite, edit loader Feb 12, 2016
main.py Merge branch 'master' of github.com:carpedm20/visual-analogy-tensorflow Feb 12, 2016
utils.py add new results Feb 14, 2016

README.md

Deep Visual Analogy-Making

Tensorflow implementation of Deep Visual Analogy-Making. The matlab code of the paper can be found here.

model

This implementation contains a deep network trained end-to-end to perform visual analogy making with

  1. Fully connected encoder & decoder networks
  2. Analogy transformations by vector addition and deep networks (vector multiplication is not implemented)
  3. Regularizer for manifold traversal transformations

This implementation conatins:

  1. Analogy transformations of shape dataset
    • with objective for vector-addition-based analogies (L_add)
    • with objective for multiple fully connected layers (L_deep)
    • with manifold traversal transformations

Prerequisites

Usage

First, you need to download the dataset with:

$ ./download.sh

To train a model with shape dataset:

$ python main.py --dataset shape --is_train True

To test a model with shape dataset:

$ python main.py --dataset shape 

Results

Result of analogy transformations of shape dataset with fully connected layers (L_deep) after 1 day of training.

From top to bottom for each : Reference, output, query, target, prediction, manifold prediction after 2 steps, and manifold prediction after 3 steps.

  • Change on angle

training in progress

  • Change on scale

training in progress

  • Change on x position

training in progress

  • Change on y position

training in progress

(in progress)

Training details

training in progress

Reference

Author

Taehoon Kim / @carpedm20