README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - object-detection
  - AgTech
  - transformers
library_name: pytorch
inference: false
datasets:
  - Laudando-Associates-LLC/pucks
base_model: Laudando-Associates-LLC/d-fine
base_model_relation: finetune
model-index:
  - name: D-FINE Large
    results:
      - task:
          type: object-detection
          name: Object Detection
        dataset:
          type: Laudando-Associates-LLC/pucks
          name: L&A Pucks Dataset
          config: default
          split: validation
        metrics:
          - type: mean_average_precision
            name: mAP@[IoU=0.50:0.95]
            value: 0.828
          - type: mean_average_precision
            name: mAP@0.50
            value: 0.976
          - type: mean_average_precision
            name: mAP@0.75
            value: 0.957
          - type: recall
            name: AR@[IoU=0.50:0.95 | maxDets=100]
            value: 0.886
          - type: recall
            name: AR@0.50
            value: 0.994
          - type: recall
            name: AR@0.75
            value: 0.97
          - type: f1
            value: 0.929
          - type: precision
            value: 0.918
          - type: recall
            value: 0.94
          - type: iou
            value: 0.785

D-FINE Large

This repository contains the D-FINE Large model, a real-time object detector designed for efficient and accurate object detection tasks.

Try it in the Browser

You can test this model using our interactive Gradio demo:

Model Overview

• Architecture: D-FINE Large

• Parameters: 31.2M

• Performance:

  • mAP@[0.50:0.95]: 0.828

  • mAP@[0.50]: 0.976

  • AR@[0.50:0.95]: 0.886

  • F1 Score: 0.929

• Framework: PyTorch / ONNX

• Training Hardware: 2× NVIDIA RTX A6000 GPUs

Download

Format	Link
ONNX
PyTorch

Usage

To utilize this model, ensure you have the shared D-FINE processor:

from transformers import AutoProcessor, AutoModel

# Load processor
processor = AutoProcessor.from_pretrained("Laudando-Associates-LLC/d-fine", trust_remote_code=True)

# Load model
model = AutoModel.from_pretrained("Laudando-Associates-LLC/d-fine-large", trust_remote_code=True)

# Process image
inputs = processor(image)

# Run inference
outputs = model(**inputs, conf_threshold=0.4)

Evaluation

This model was trained and evaluated on the L&A Pucks Dataset.

License

This model is licensed under the Apache License 2.0.

Citation

If you use D-FINE or its methods in your work, please cite the following BibTeX entries:

@misc{peng2024dfine,
      title={D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement},
      author={Yansong Peng and Hebei Li and Peixi Wu and Yueyi Zhang and Xiaoyan Sun and Feng Wu},
      year={2024},
      eprint={2410.13842},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}