Roboflow

Detect Objects (RF DETR)

Runs a bound RF-DETR checkpoint locally over each Image, building one per-detection record and projecting it onto the connected output shape: boxes, geometry, labels, a count, or an overlay, filtered by confidence.

Segment Image (RF DETR)

Transformer instance segmentation on an Image with an RF-DETR-Seg weights file. The sink resolves the projection: mask-plus-box pairs, masks, boxes, parallel arrays, a merged Mask, a UInt64 count, or a colourised label Image.

Detect Landmarks (RF DETR)

Detects every person in a single Image and emits their COCO-17 body keypoints in one RF-DETR forward pass — box and keypoints predicted jointly, no separate detector or top-down crop stage — packaged per person as [[Landmark]].