Deploy to Roboflow

Deploy your fine-tuned RF-DETR model to Roboflow to run cloud inference and build multi-step computer vision applications.

Deploy your model

Upload your model to Roboflow

Call deploy_to_roboflow() with your workspace ID, project ID, version number, and API key.

Object detection
Image segmentation

from rfdetr import RFDETRNano

x = RFDETRNano(pretrain_weights="<path/to/pretrain/weights/dir>")
x.deploy_to_roboflow(
    workspace="<your-workspace>",
    project_id="<your-project-id>",
    version=1,
    api_key="<YOUR_API_KEY>",
)

from rfdetr import RFDETRSegMedium

x = RFDETRSegMedium(pretrain_weights="<path/to/pretrain/weights/dir>")
x.deploy_to_roboflow(
    workspace="<your-workspace>",
    project_id="<your-project-id>",
    version=1,
    api_key="<YOUR_API_KEY>",
)

Run inference with Roboflow Inference

Use get_model from the inference package to load your deployed model and run predictions.

Object detection
Image segmentation

import supervision as sv
from inference import get_model
from PIL import Image
from io import BytesIO
import requests

url = "https://media.roboflow.com/dog.jpeg"
image = Image.open(BytesIO(requests.get(url).content))

model = get_model("rfdetr-large")  # replace with your Roboflow model ID

predictions = model.infer(image, confidence=0.5)[0]

detections = sv.Detections.from_inference(predictions)

labels = [prediction.class_name for prediction in predictions.predictions]

annotated_image = image.copy()
annotated_image = sv.BoxAnnotator().annotate(annotated_image, detections)
annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections, labels)

sv.plot_image(annotated_image)

import supervision as sv
from inference import get_model
from PIL import Image
from io import BytesIO
import requests

url = "https://media.roboflow.com/dog.jpeg"
image = Image.open(BytesIO(requests.get(url).content))

model = get_model("rfdetr-seg-small")  # replace with your Roboflow model ID

predictions = model.infer(image, confidence=0.5)[0]

detections = sv.Detections.from_inference(predictions)

labels = [prediction.class_name for prediction in predictions.predictions]

annotated_image = image.copy()
annotated_image = sv.MaskAnnotator().annotate(annotated_image, detections)
annotated_image = sv.LabelAnnotator().annotate(annotated_image, detections, labels)

sv.plot_image(annotated_image)

The first time you run your model, Inference downloads and caches the model weights locally. Subsequent runs use the cached weights and start faster.