Non-stationary texture synthesis by adversarial expansion

Information

• Paper topic: Images
• Software type: Code
• Able to run a replicability test: True
• Replicability score: 5
• Software language: Python
• License: MIT
• Build mechanism: Not applicable (python, Matlab..)
• Dependencies: pytorch/cuda
• Documentation score {0,1,2}: 1
• Reviewer: Julie Digne <julie.digne@liris.cnrs.fr>
• Time spent for the test (build->first run, timeout at 100min): 100min

Source code information

• Code URL: https://github.com/jessemelpolio/non-stationary_texture_syn
• Git commit hash: c74b8c0adb3a8a0831f491958b827811977108b3
• Software Heritage link:

Comments

The code is supposed to support python3 (script train_half_style starts with python3), but several changes need to be made to make it work with python3: tensor[0] should be replaced by tensor.item(), xrange() should be replaced by range(). Needs also visdom and dominate package which were not listed in the README.

If you want to contribute with another review, please follow these instructions.

Please consider to cut/paste/edit the raw JSON data attached to this paper.