Progress for week 5 (2016)

Fra Robin

(Forskjeller mellom versjoner)
Gå til: navigasjon, søk
(Eirik Sundet)
 
(Én mellomrevisjon ikke vist.)
Linje 25: Linje 25:
* Compare test accuracy against training iterations
* Compare test accuracy against training iterations
* Plot ROC curves for the test data
* Plot ROC curves for the test data
-
* Explore the deep visualization toolbox
 
* Surgically remove neurons
* Surgically remove neurons
Linje 32: Linje 31:
* Done for reinitialized model and fully trained model up to iter #240K
* Done for reinitialized model and fully trained model up to iter #240K
* Done
* Done
-
* Got it up and running, next is the evolutionary add-on
 
* Delayed
* Delayed
 +
Extra:
Extra:
-
*
+
* Got the deep visualization toolbox up and running, next is the evolutionary add-on
== [[user:Fredrsae|Fredrik]] ==
== [[user:Fredrsae|Fredrik]] ==
Linje 43: Linje 42:
* Thesis writing (Things not related to results)
* Thesis writing (Things not related to results)
 +
 +
== [[user:Perwn|Per Wessel]] ==
 +
=== Budget ===
 +
* Write thesis
 +
 +
=== Accounting ===
 +
* Got feedback on data from NILU.
 +
* They want me to redo some of the data gathering, previous data not sufficient.
=== Accounting ===
=== Accounting ===
*
*

Nåværende revisjon fra 11. feb 2016 kl. 15:14

Innhold

Student template (copy this for your entry)

Budget

  • Todo 1
  • Todo 2

Accounting

  • Done 1
  • Done 2

Eirik Sundet

Budget

  • Thesis writing

Accounting

  • Done 1

Also:


Kai Wig

Budget

  • Further fine tune Kitti CNN model
  • Compare test accuracy against training iterations
  • Plot ROC curves for the test data
  • Surgically remove neurons

Accounting

  • Trained with/without locked Conv layers, with/without reinitialized top layers
  • Done for reinitialized model and fully trained model up to iter #240K
  • Done
  • Delayed

Extra:

  • Got the deep visualization toolbox up and running, next is the evolutionary add-on

Fredrik

Budget

  • Implement IT&E
  • Fix multithreading (low prio)
  • Thesis writing (Things not related to results)


Per Wessel

Budget

  • Write thesis

Accounting

  • Got feedback on data from NILU.
  • They want me to redo some of the data gathering, previous data not sufficient.

Accounting

Personlige verktøy