RF-DETR 1.4.0

Changelog

Warning

Starting with version 1.4.0, RF-DETR drops support for Python 3.9. If your environment still relies on Python 3.9, stay on RF-DETR 1.3.x or upgrade your Python runtime to 3.10 or newer.

🚀 Added

• New pre-trained checkpoints. Object detection includes new L, XL, and 2XL checkpoints. Instance segmentation includes N, S, M, L, XL, and 2XL checkpoints. (#539)

  

  import requests
  import supervision as sv
  from PIL import Image
  from rfdetr import RFDETRSegMedium
  from rfdetr.util.coco_classes import COCO_CLASSES
  
  model = RFDETRSegMedium()
  
  image = Image.open(requests.get('https://media.roboflow.com/dog.jpg', stream=True).raw)
  detections = model.predict(image, threshold=0.5)
  
  labels = [
      f"{COCO_CLASSES[class_id]}"
      for class_id
      in detections.class_id
  ]
  
  annotated_image = sv.MaskAnnotator().annotate(image, detections)
  annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections, labels)

  rf-detr-segmentation-promo.mp4

• Support for training object detection and instance segmentation models using datasets in YOLO format. (#569)

🌱 Changed

• Simplified project dependencies by removing cython, fairscale, timm, accelerate, ninja, einops, pandas, pylabel, and open_clip_torch from pyproject.toml. This reduces the dependency footprint and makes RF-DETR easier to install alongside other Python packages. (#571)

🔧 Fixed

• Fixed precision, recall, and F1 computation during confidence sweeps. This resolves an issue where recall values were identical across classes and aligns per-class and class-averaged metrics with expected COCO-style behavior. (#545)

🏆 Contributors

@isaacrob (Isaac Robinson), @probicheaux (Peter Robicheaux), @Matvezy (Matvei Popov), @mkaic (Kai Christensen), @anujonthemove (Anuj Khandelwal), @brunopicinin (Bruno Cardoso), @capjamesg (James Gallagher), @Borda (Jirka Borovec), @SkalskiP (Piotr Skalski)