Vision Analysis

Models

Every detection family on Vision Analysis, grouped by architecture. Open a family for its variants, specifications, and full hardware breakdown.

Real-time CNN detectors4 families

Single-stage convolutional detectors. These run broadly, including on edge NPUs.

FamilyOrganizationVariantsParameters
YOLOXMegvii60.9 - 99.1MView family
PicoDetBaidu PaddlePaddle31.0 - 3.3MView family
YOLOv9Academia Sinica42.0 - 25.5MView family
YOLO-NASDeci AI (acquired by NVIDIA)319.0 - 67.0MView family

Transformer (DETR) detectors8 families

Detection-transformer architectures. Higher accuracy ceilings; GPU and CPU runtimes.

FamilyOrganizationVariantsParameters
DEIMv2Intellindust AI Lab80.5 - 50.3MView family
D-FINEUSTC54.0 - 62.0MView family
DEIMIntellindust AI Lab54.0 - 62.0MView family
ECDetIntellindust AI Lab49.9 - 49.0MView family
RT-DETRv4Intellindust AI Lab410.0 - 62.0MView family
RT-DETRBaidu720.0 - 76.0MView family
RT-DETRv2Baidu520.0 - 76.0MView family
RF-DETRRoboflow430.5 - 33.9MView family

Run any model with one line

LibreYOLO has the best catalogue of state-of-the-art detectors, all behind one MIT-licensed Python API.

from libreyolo import LibreYOLO, SAMPLE_IMAGE

# LibreYOLO has the best catalogue of state-of-the-art models.
model = LibreYOLO("LibreRFDETRl.pt")           # RF-DETR-L (transformer flagship)
results = model(SAMPLE_IMAGE, save=True)        # run inference, save the annotated image

# Swap in any other model, same one-line API (weights auto-download):
#   LibreYOLO("LibreYOLO9c.pt")      # YOLO9-C
#   LibreYOLO("LibreYOLOXx.pt")      # YOLOX-X
#   LibreYOLO("LibreDFINEx.pt")      # D-FINE-X
#   LibreYOLO("LibreRTDETRr50.pt")   # RT-DETR-R50