-
Notifications
You must be signed in to change notification settings - Fork 38
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
Add 'resume training' feature #6
Labels
enhancement
New feature or request
Comments
CBroz1
changed the title
Training start point is encoded in
Add 'resume training' feature
May 5, 2022
pose_cfg.yaml
partially addressed in upcoming workflow pr |
This function provides the ability to update the training config file to point to the relevant checkpoint. The team will consider migrating this code to the element itself. |
MilagrosMarin
pushed a commit
to MilagrosMarin/element-deeplabcut
that referenced
this issue
Aug 3, 2023
Add issue templates
ttngu207
added a commit
to ttngu207/element-deeplabcut
that referenced
this issue
Sep 20, 2024
Save config to outbox as dj_dlc_config
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Our current draft manages
config.yaml
within the dataframe, but doesn't make adjustments to the model training file located under models:<project_folder>/dlc-models/iteration-<#>/<scorer>/train/pose_cfg.yaml
To resume training from the previous training snapshot, we would need to modify the
init_weights
value to a full path without extensiondlc-models/iteration-<#>/<scorer>/train/snapshot-<#>
The text was updated successfully, but these errors were encountered: