What's new 🔥
New model sizes
RF-DETR 1.2.0 introduces three new, state-of-the-art, model sizes for object detection:
- Nano (
RFDETRNano) - Small (
RFDETRSmall) - Medium (
RFDETRMedium)
With the rfdetr Python package, you can train and run models with these architectures.
The training API is as follows:
from rfdetr import RFDETRNano
model = RFDETRNano()
model.train(
dataset_dir=<DATASET_PATH>,
epochs=10,
batch_size=4,
grad_accum_steps=4,
lr=1e-4,
output_dir=<OUTPUT_PATH>
)Trained models can also be deployed with Roboflow Inference with the new deploy_to_roboflow function. This allows you to provision a serverless cloud API for running your model, as well as deploy your model in a Roboflow Workflow or with a Roboflow Inference server:
from rfdetr import RFDETRNano
x = RFDETRNano(pretrain_weights="<path/to/prtrain/weights/dir>")
x.deploy_to_roboflow(
workspace="<your-workspace>",
project_ids=["<your-project-id>"],
api_key="<YOUR_API_KEY>"
)rf-detr-1.2.0-promo.mp4
New documentation
RF-DETR now has its own documentation website. This website has tutorials on running RF-DETR with base weights, fine-tuning RF-DETR models, and deploying RF-DETR models. You can also see auto-generated docstring documentation for the main model classes.
🏆 Contributors
@probicheaux @isaacrob-roboflow @Matvezy @MadeWithStone @SkalskiP @capjamesg
