Dev/update train use dataset #35
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Includes offline and online data loading methods for different use cases to invoke as appropriate.
Frame identifier returned has no bearing on training, but is utilized in plotting and within the training framework. This more benefits from a label that is reflective of frame number than the possibly arbitrary IDs assigned to image objects in the COCO file.
Also adds a function to recreate a dataset from a given hyperparameter config as from a training run that produced a given model. This is to be used by the prediction code to generate a dataset such that congruent vectorization will occur as done during training. Updates the latest M2 experiment file as a test-bed.
Closed
cameron-a-johnson
approved these changes
Oct 25, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Overhauls the dataset usage in TCN-HPL to make use of truth, detection and pose input COCO files. This still maintains training functionalities, achieving the same or better accuracy on M2 at least than previous training runs, and supports much more direct utilization by down-stream users, i.e. the targetted ROS streaming inference use-case.