Skip to content

PyTorch implementation of A Neural Algorithm of Artistic Style

Notifications You must be signed in to change notification settings

safwankdb/Neural-Style-Transfer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Neural-Style-Transfer

PyTorch implementation of A Neural Algorithm of Artistic Style by Leon A. Gatys, et al.

Progress

This is the progress of the first few iterations

progress progress

Implementation Details

  • The hyperparameters are same as used in the paper.
  • All the code was written and ran on Google Colab.
  • As in the paper, conv1_1, conv2_1, conv3_1, conv4_1, conv5_1 are used for style loss.
  • SImilarly, conv4_2 is used for content loss.
  • PyTorch's forward hooks are used to extract intermediate feature maps.
  • VGG19's MaxPool2d layers were replaced by AvgPool2d layers.

Requirements

torch
torchvision
numpy
matplotlib
Pillow
imageio

References

  1. Leon A. Gatys, et al. A Neural Algorithm of Artistic Style [arxiv]

About

PyTorch implementation of A Neural Algorithm of Artistic Style

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages