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

Retraining of the Segmentation #4

Open
joweyel opened this issue Aug 10, 2021 · 0 comments
Open

Retraining of the Segmentation #4

joweyel opened this issue Aug 10, 2021 · 0 comments

Comments

@joweyel
Copy link

joweyel commented Aug 10, 2021

Is there a possibility to retrain the network on my own generated synthetic dataset without losing the current performance of the network? I would like to just retrain some certain layers to get even better performance on my own dataset, or is the architecture too special for that?
I would like to avoid to retrained the network from scratch? For generating the synthetic dataset I used SceneNet RGB-D with custom rooms and objects.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@joweyel