Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

multi-target neural net regression #23

Closed
5 tasks done
beniz opened this issue Sep 3, 2015 · 1 comment
Closed
5 tasks done

multi-target neural net regression #23

beniz opened this issue Sep 3, 2015 · 1 comment
Assignees
@beniz
Labels
kind:API kind:model kind:neural net mllib:caffe

Comments

@beniz
Copy link
Collaborator

beniz commented Sep 3, 2015

As a follow up to #1, see https://github.com/beniz/deepdetect/issues/1#issuecomment-137553339

Steps:

  • gather a small and well-known dataset for multi-target regression that implementation can be checked against easily
  • set a working training / prediction model with Caffe
  • include the multi-target model definition to API as needed
  • add to model template construction code
  • add to unit tests

Discussing whether this does use the scheme recommended in BVLC/caffe#881 (comment) or some other (simpler ?) way that requires patching Caffe, might be required.

(Also, multi-target regression (and classification) do not mix well with the image connector typically, that uses the repository name as the single class (no regression supported yet) label.)
@beniz beniz self-assigned this Sep 3, 2015
beniz added a commit that referenced this issue Nov 6, 2015
@beniz
added support for multi-target regression and classification with Caf…
1bad87a 
…fe, based on concat + slicing of data and labels, ref #23
beniz added a commit that referenced this issue Nov 6, 2015
@beniz
unit test for multi-target regression with Caffe, ref #1, #23
de832bb
@beniz
Copy link
Collaborator Author

beniz commented Nov 6, 2015

Now supported via ntargets parameter for regression at service creation, see API. Unit tested.

@beniz beniz closed this as completed Nov 6, 2015
beniz added a commit that referenced this issue Nov 27, 2015
@beniz
neural net regression format with Caffe in prediction mode, ref #23
3fb72de
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@beniz beniz

Labels
kind:API kind:model kind:neural net mllib:caffe
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@beniz