LucasSaiGao/src

TopoAgent Dataset

This dataset contains training and validation data for the TopoAgent project, which focuses on detecting topological errors in segmentation masks.

Dataset Structure

This dataset includes the following directories:

• rft_v2/ - 56.37 KB

Data Format

The dataset contains JSON files with annotations in the following format:

{
  "id": "example_id",
  "image": [
    "path/to/original.png",
    "path/to/mask.png"
  ],
  "conversations": [
    {
      "from": "human",
      "value": "<image>\n<image>\n[prompt]"
    },
    {
      "from": "gpt",
      "value": "<answer>[annotations]</answer>"
    }
  ]
}

Path Configuration

The JSON files contain absolute paths starting with /data/meilong/projects/topoagent/.

To use this dataset on your local machine:

1. Download the dataset
2. Use the replace_paths.py script to update paths:

python replace_paths.py \
    --input downloaded_file.json \
    --output updated_file.json \
    --old-prefix "/data/meilong/projects/topoagent/" \
    --new-prefix "/your/local/path/"

Error Types

The dataset includes annotations for four types of topological errors:

1. broken_connection: Missing connections between segments
2. spurious_connection: False connections in the segmentation
3. missing_branch: Branches that should exist but are missing
4. extra_branch: Branches that shouldn't exist but are present

Citation

If you use this dataset, please cite:

@dataset{topoagent_dataset,
  title={TopoAgent Dataset},
  author={Your Name},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/datasets/LucasSaiGao/src}
}

License

This dataset is released under CC-BY-NC-4.0 license.