Move some reader logic into abstract base class and implement reader for all-class godot data #17
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
|
I'm hella petty so I force-pushed to change the author of the commits I made on the lab PC to myself instead of vince |
|
The tasks are for choosing which sub-directory to output to |
|
If there's an online copy of the dataset, can you link it here so that I can test it out locally? Also, can you briefly specify what the expected input for this script is and how to set it up reproducibly? That can go in the class description. |
MinhxNguyen7
requested changes
May 16, 2024
| # same as superclass constructor but without path checking because we need to swap order | ||
| # of task and directory (e.g. train/images -> images/train) | ||
|
|
||
| def read( |
There was a problem hiding this comment.
From my understadning, this would only support classifiation, right? Why don't we just implement detection support as well? It should just be a little bit of easy math.
…urn 4 bounding boxes per target, for each sub-label
|
ok @MinhxNguyen7 this is done for real now |
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Outdated suggestions cannot be applied.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.
Summary
The new Godot reader doesn't actually use the abstract base class because it takes a Godot dataset as input instead of a dataset that's YOLO-formatted.
I also edited
YoloWriterto print out one of the errors in addition to raising it so it's visible during multiprocessingTesting
/home/forge/eric/uavf_2024/imaging_training_2024py -m yolo_to_yolo.run_godot_readerThis will create a folder in
/datasets/godot_processed. If you want to reproduce on a different machine, you can scp down/datasets/godot_raw/godot_data_small_100and edit the input/output paths of the main script.