Use MNIST160 #10069
Merged
Use MNIST160 #10069
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
New 160-image MNIST subset composed of first 8 examples of each class. Suitable for fast CI. Signed-off-by: Glenn Jocher <[email protected]>
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Outdated suggestions cannot be applied.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.
New 160-image MNIST subset composed of first 8 examples of each class. Suitable for fast CI.
Signed-off-by: Glenn Jocher [email protected]
🛠️ PR Summary
Made with ❤️ by Ultralytics Actions
🌟 Summary
Enhancements to the image classification training and validation process within the YOLOv5 CI workflow.
📊 Key Changes
mnist2560tomnist160for training, validation, and prediction steps.--imgsz 224from theexport.pycommand, simplifying the export invocation.🎯 Purpose & Impact
mnist2560tomnist160is likely a move to use a dataset variant with different characteristics, which may improve training speed or model performance on smaller datasets.--imgsz) from the export command could be aimed at standardizing the export process or reducing the complexity of the command. It may impact the exported model's compatibility with specific image sizes if defaults are not comprehensive.These changes aim to refine the training and evaluation pipeline, positively affecting developers by providing more streamlined commands and potentially better model performance and training speed. Additionally, it can aid users who follow the CI workflow as a reference for their own projects. 🤖✨