DenseCap. Automatically finds and describes everything in a photo.

github.com/jcjohnson/densecap

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

June 2017
  • Update README.md
April 2017
  • Merge pull request #71 from ojotoxy/patch-1
  • Virtualenv commands were out of order
September 2016
  • Update README.md
August 2016
  • Merge pull request #33 from agude/total_cost_fix
  • Fix summing of losses
July 2016
  • Merge pull request #18 from ruotianluo/master
  • Fix some small bugs:
May 2016
  • add script for feature extraction
April 2016
  • Merge branch 'soumith-patch-1'
  • fix stn module for API change
  • only require loadcaffe when initializing model
  • remove cutorch from net utils
  • change elephant example image
  • add elephant image
  • Update README.md
  • Update FLAGS.md
  • Merge branch 'master' of https://github.com/jcjohnson/densecap
  • change some of the default training options
  • Update FLAGS.md