Training a neural network to map from x,y of an images pixels to r,g,b.
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.
images
README.md
image-learner.ipynb
image-learner.py

README.md

Learning to reconstruct an image from pixel coordinates

Train a neural network to map from x and y coordinate of each pixel to the pixels r,g,b values. The network has 2 inputs (x and y), several fully connected (highway) layers and three outputs (r, g and b).

See implementation in image-learner.ipynb

Examples

Input:

example1

Sample Outputs:

after 12 epochs with a network of width 6 and depth 35

example1

after 520 epochs with a network of width 150 and depth 5

example1

Input:

example1

Sample Outputs:

after 4 epochs with a network of width 6 and depth 25

example1

after 14 epochs with a network of width 6 and depth 25

example1

Input:

example1

Sample Outputs:

after 2 epochs with a network of width 50 and depth 20

example1

after 142 epochs with a network of width 50 and depth 20

example1

Input:

example1

Sample Outputs:

after 7 epochs with a network of width 6 and depth 25

example1)

after 45 epochs with a network of width 6 and depth 25

example1

Input:

example1

Sample Outputs:

after 8 epochs with a network of width 70 and depth 5

example1

after 75 epochs with a network of width 70 and depth 5

example1