Differentiable Programming for Image Processing and Deep Learning in Halide

SIGGRAPH 2018


Reviews

Information

  • Paper topic: Images
  • Software type: Code
  • Able to run a replicability test: True
  • Replicability score: 3
  • Software language: C/C++
  • License: MIT
  • Build mechanism: Makefile, CMakeLists
  • Dependencies: llvm
  • Documentation score {0,1,2}: 2
  • Reviewer: Julie Digne <julie.digne@liris.cnrs.fr>
  • Time spent for the test (build->first run, timeout at 100min): 100min

Source code information

Comments

I was able to perform automatic differentiation (gamma correction example in the paper) however most filter examples in the paper did not come with code to reproduce and I was unable to reproduce them in a timely manner.

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.