Chicken RT-DETRv2

Fine-tuned chicken object detector used by Khoroos.

  • Architecture: RTDetrV2ForObjectDetection.
  • Output class: Chicken (ID 0).
  • Processor resize: 640 pixels wide by 480 pixels high.
  • Checkpoint dtype: float32.

Load

Authenticate with a Hugging Face account authorized to access this private repository.

from transformers import AutoImageProcessor, AutoModelForObjectDetection

repo_id = "amirivojdan/chicken_rtdetrv2"
processor = AutoImageProcessor.from_pretrained(repo_id, token=True)
model = AutoModelForObjectDetection.from_pretrained(repo_id, token=True).eval()

The model produces detection boxes and scores. Use the processor's post_process_object_detection with the original image dimensions, then clamp coordinates to the image bounds before exporting annotations.

These outputs support detection statistics and tracking; no welfare interpretation is provided. Evaluation metrics are not included in this export.

License

This fine-tuned model is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license (CC BY-NC-SA 4.0). See LICENSE for the full terms.

Attribution: Ahmad Amirivojdan, amirivojdan/chicken_rtdetrv2. Indicate any modifications when sharing the model. Third-party components retain their applicable licenses and notices.

Downloads last month
12
Safetensors
Model size
42.9M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support