Implementation:Roboflow Rf detr RFDETR Deploy To Roboflow
Appearance
| Knowledge Sources | |
|---|---|
| Domains | Deployment, MLOps |
| Last Updated | 2026-02-08 15:00 GMT |
Overview
Concrete tool for deploying trained RF-DETR models to the Roboflow platform.
Description
RFDETR.deploy_to_roboflow() packages the model's state dict and args into a temporary weights.pt file, authenticates with Roboflow using the provided API key (or ROBOFLOW_API_KEY env var), and uploads via the version.deploy() method. The model size string (e.g. "rfdetr-base") is included for Roboflow to configure the inference server correctly.
Usage
Call on a trained RFDETR model instance after fine-tuning to deploy to Roboflow.
Code Reference
Source Location
- Repository: rf-detr
- File: rfdetr/detr.py
- Lines: L405-458
Signature
def deploy_to_roboflow(
self,
workspace: str,
project_id: str,
version: str,
api_key: str = None,
size: str = None,
) -> None:
"""
Deploy the trained RF-DETR model to Roboflow.
Args:
workspace: Roboflow workspace name
project_id: Target project ID
version: Project version number
api_key: API key (falls back to ROBOFLOW_API_KEY env var)
size: Model size string (e.g. "rfdetr-base"); auto-detected from class
"""
Import
from rfdetr import RFDETRBase # or any size variant
I/O Contract
Inputs
| Name | Type | Required | Description |
|---|---|---|---|
| workspace | str | Yes | Roboflow workspace name |
| project_id | str | Yes | Target project ID |
| version | str | Yes | Project version number |
| api_key | Optional[str] | No | API key (default: ROBOFLOW_API_KEY env var) |
| size | Optional[str] | No | Model size string (auto-detected from model class) |
Outputs
| Name | Type | Description |
|---|---|---|
| Deployed model | Remote | Model available on Roboflow platform for inference |
Usage Examples
Deploy After Training
from rfdetr import RFDETRBase
# Train model
model = RFDETRBase()
model.train(dataset_dir="/path/to/dataset", epochs=50)
# Deploy to Roboflow
model.deploy_to_roboflow(
workspace="my-workspace",
project_id="my-detection-project",
version="1",
api_key="your_api_key",
)
Related Pages
Implements Principle
Requires Environment
Page Connections
Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment