LazyCube Computer Vision Project
Updated a year ago
Metrics
LazyCube Data Set
Images for training a TFL model for detecting rubick's cube square colours and faces.
Annotations
Annotations should completely cover the subject. For example, a box should completely encapsulate a square colour or face. No more, no less.
Classes
- Blue
- Green
- White
- Yellow
- Red
- Orange
- Face
Annotating Pre-Annotated images
Pre-annotated images, for example, an output from trained model, need to adjusted to be added to the dataset with no issues. Often, colour or face annotations are missing, or positions/size need to be adjusted to properly fit the subject.
Annotation Examples
Good Examples
Bad Examples
Bad examples mostly include annotations with poor placement, where not all of the feature (colour sticker or face) is covered by a box. As a rule of thumb, you want to encapsulate the entirety of the feature and nothing else.
Use This Trained Model
Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.
Build Computer Vision Applications Faster with Supervision
Visualize and process your model results with our reusable computer vision tools.
Cite This Project
If you use this dataset in a research paper, please cite it using the following BibTeX:
@misc{
lazycube_dataset,
title = { LazyCube Dataset },
type = { Open Source Dataset },
author = { LazyCube },
howpublished = { \url{ https://universe.roboflow.com/lazycube/lazycube } },
url = { https://universe.roboflow.com/lazycube/lazycube },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2023 },
month = { may },
note = { visited on 2024-09-24 },
}