python -m venv .venv source .venv/bin/activate python -m pip install --upgrade pip pip install -U ultralytics opencv-python numpy

pip install -r requirements.txt

README roboflow txt

Darts - v2 2024-02-06 9:41pm

This dataset was exported via roboflow.com on February 11, 2024 at 5:57 PM GMT

Roboflow is an end-to-end computer vision platform that helps you

• collaborate with your team on computer vision projects
• collect & organize images
• understand and search unstructured image data
• annotate, and create datasets
• export, train, and deploy computer vision models
• use active learning to improve your dataset over time

For state of the art Computer Vision training notebooks you can use with this dataset, visit https://github.com/roboflow/notebooks

To find over 100k other datasets and pre-trained models, visit https://universe.roboflow.com

The dataset includes 10000 images. Points are annotated in YOLOv8 format.

The following pre-processing was applied to each image:

• Auto-orientation of pixel data (with EXIF-orientation stripping)
• Resize to 640x640 (Stretch)

No image augmentation techniques were applied.

Preparing a flat folder for training

If you start with one folder containing mixed image files and YOLO label files, you can convert it into this repo's train/valid/test dataset layout with:

python scripts/split_flat_dataset.py \
  --input /path/to/flat_folder \
  --output /path/to/output_dataset \
  --train-ratio 0.7 \
  --valid-ratio 0.2 \
  --test-ratio 0.1 \
  --seed 42

The script:

• matches files by basename, for example image_001.jpg with image_001.txt
• copies matched pairs into train, valid, and test
• creates images/ and labels/ folders inside each split
• reports unmatched files instead of silently dropping them