Difference between revisions of "DSC180F20W10"

From Immersive Visualization Lab Wiki
Jump to: navigation, search
(Created page with "=Final Replication Checkpoint= * Report: summary of replication result, shortcomings, possible improvements * Code: Functional Grad-CAM code with COCO data set")
 
(Report)
 
(10 intermediate revisions by one user not shown)
Line 1: Line 1:
 
=Final Replication Checkpoint=
 
=Final Replication Checkpoint=
  
* Report: summary of replication result, shortcomings, possible improvements
+
The goal of the final project is to apply the Grad-CAM algorithm to the COCO dataset.
* Code: Functional Grad-CAM code with COCO data set
+
 
 +
==Report==
 +
 
 +
Write a 3-6 pages long report on your final replication project. Include at least the following components:
 +
 
 +
* A title for your report
 +
* Your team members' names
 +
* Summarize your replication result
 +
** Include at least six images with heatmaps: three with correct predictions and three with incorrect predictions.
 +
* Discuss shortcomings of your approach
 +
* List possible improvements
 +
* Conclusions: summarize what you learned from the project
 +
 
 +
==Code==
 +
 
 +
* Develop functional Grad-CAM code which uses the COCO data set.
 +
* Develop code that generates an analysis and figures for results.
 +
* You can [https://github.com/jacobgil/pytorch-grad-cam use this code as a basis].

Latest revision as of 23:51, 13 December 2020

Final Replication Checkpoint

The goal of the final project is to apply the Grad-CAM algorithm to the COCO dataset.

Report

Write a 3-6 pages long report on your final replication project. Include at least the following components:

  • A title for your report
  • Your team members' names
  • Summarize your replication result
    • Include at least six images with heatmaps: three with correct predictions and three with incorrect predictions.
  • Discuss shortcomings of your approach
  • List possible improvements
  • Conclusions: summarize what you learned from the project

Code

  • Develop functional Grad-CAM code which uses the COCO data set.
  • Develop code that generates an analysis and figures for results.
  • You can use this code as a basis.