Differentiable Programming for Image Processing and Deep Learning in Halide

Information

• Paper topic: Image
• Software type: Code
• Able to run a replicability test: True
• Replicability score: 3
• License: MIT
• Build mechanism: Makefile, CMakeLists
• Dependencies: llvm
• Documentation score {0,1,2}: 2
• Reviewer: Julie Digne

Source code information

• Code URL: https://github.com/halide/Halide
• Git commit hash: 19e66f9673c0a153f57c42c1b2f1c7696914582d
• Software Heritage link:

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.

There are two options to add a review to this article:

• Open a pull request at https://github.com/dcoeurjo/ReplData-private
• Fill the form below (this option requires manual work and might be avoided if possible):
  TODO: ADD FORM