Supported models
There are three ways you can deploy models with Inference:
- Deploy a model hosted on Roboflow onto your device.
- Upload suported model weights to Roboflow, then deploy to your device.
- Deploy a foundation model out-of-the-box.
The pages linked above will walk you through each of these options.
Supported Custom Models¶
The following custom models are supported:
- YOLOv5 (Segmentation, Object Detection)
- YOLOv7 (Segmentation)
- YOLOv8 (Classification, Segmentation, Object Detection)
- YOLO-NAS (Coming soon)
Supported Foundation Models¶
- CLIP
- CogVLM
- DocTR
- Grounding DINO
- L2CS-Net
- Segment Anything
- YOLOWorld