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.

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

General Filter & Portrate Mode Filter - train model [skeleton] #61

Open
XiaoSong9905 opened this issue Mar 23, 2020 · 0 comments
Open

Comments

@XiaoSong9905
Copy link
Contributor

XiaoSong9905 commented Mar 23, 2020

Info

  1. each model corrsponding to a specific filter
  2. take time to train a model
  3. upload / share trained model weight to Xiao, so that he can pack the model
  4. trained model weight is stored in local computer, model is packed into servable and upload to zenhub. See "pack model into servavle card"

Link to feature

  1. model weight source file is kept on local machine because it's too large for github to store
  2. model weight is packed into servable and then packed into docker and pubslihed here https://hub.docker.com/r/xiaosong99/servable

Progress

  1. finish, model weight are uploaded to docker hub

User Story & Acceptance Criteria

General Filter: https://docs.google.com/document/d/1YU66XGAY_96yoz0vlgMPM-049zOeC4QVQgMvJiivYsE/edit?usp=sharing

Portrate Mode Filter : https://docs.google.com/document/d/1BMszGmVqfQa7ZOoLGFx_vB3N_HeCxCEe_6KgkWVSmRo/edit?usp=sharing

Additional Acceptance Criteria:
model generate comparable result

@XiaoSong9905 XiaoSong9905 self-assigned this Mar 23, 2020
@XiaoSong9905 XiaoSong9905 added CORE Fature Type and removed Back End Feature Type::MVP Feature Type labels Mar 23, 2020
@XiaoSong9905 XiaoSong9905 changed the title General Filter & Portrate Mode Filter - train model (model fine tune) General Filter & Portrate Mode Filter - train model [skeleton] Mar 29, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant