CenterNet

CenterNet models an object as the center point of its bounding box and regresses every other property from a heatmap peak, so it needs no anchors and no non-maximum-suppression step. LibreYOLO ships it as an inference-only detector.

Tasks: detection
Sizes: resdcn18, dla34 at 512 px
Install: pip install libreyolo
Support tier: Inference only, since v. Predict, validate and export only. Training features do not apply.
Upstream: CenterNet by UT Austin and UC Berkeley, MIT. Paper, source
Licenses: Code MIT, weights MIT. Commercial use

Install

CenterNet needs no optional extra. Everything it imports is in the base install.

bash

pip install libreyolo

Predict

Weights download from Hugging Face on first use and are cached locally.

Python

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreCenterNetresdcn18.pt")result = model(SAMPLE_IMAGE, save=True) for box in result.boxes:    print(box.cls, box.conf, box.xyxy)

CLI

libreyolo predict model=LibreCenterNetresdcn18.pt source=https://raw.githubusercontent.com/LibreYOLO/libreyolo/release/libreyolo/assets/parkour.jpg save=True

DLA-34

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreCenterNetdla34.pt")result = model(SAMPLE_IMAGE, save=True)

The returned Results object is the one every family returns, so swapping in a different detector is a one line change. conf and max_det filter the ranked heatmap peaks; iou is accepted for API parity but has no effect, because CenterNet's top-k peak decode needs no box-IoU suppression step. See prediction for sources, streaming and result handling.

Variants

Two backbones. resdcn18 pairs a ResNet-18 trunk with deformable-convolution upsampling; dla34 pairs a DLA-34 trunk with iterative deep-aggregation upsampling. Both feed the same three dense heads (heatmap, width/height, offset) and the same input canvas.

Validate

val() returns a dictionary of metrics/ keys covering precision, recall, mAP 50 and mAP 50-95, measured against any dataset in the format you trained on.

Python

from libreyolo import LibreYOLO model = LibreYOLO("LibreCenterNetresdcn18.pt")metrics = model.val(data="my-dataset.yaml") print(metrics["metrics/mAP50-95"])print(metrics["metrics/mAP50"])

CLI

libreyolo val model=LibreCenterNetresdcn18.pt data=my-dataset.yaml

Export

Task	ONNX	TorchScript	ExecuTorch	TensorRT	OpenVINO	Paddle	MNN	RKNN	ncnn	TFLite	CoreML	Core AI
Detection	Detection to ONNX: supported.	Detection to TorchScript: supported.	Detection to ExecuTorch: supported.	Detection to TensorRT: supported.	Detection to OpenVINO: supported.	Detection to Paddle: not supported	Detection to MNN: not supported	Detection to RKNN: not supported	Detection to ncnn: not supported	Detection to TFLite: not supported	Detection to CoreML: not supported	Detection to Core AI: not supported

ONNX export requires opset 16 or newer: the deformable-convolution upsampling stage in both backbones lowers to the ONNX GridSample operator, which opset 16 introduced. Requesting an older opset raises before tracing starts.

Python

from libreyolo import LibreYOLO model = LibreYOLO("LibreCenterNetresdcn18.pt") # ONNX export needs opset 16 or newer: the deformable-convolution# upsampling stage lowers to GridSample, which opset 16 introduced.model.export(format="onnx", opset=18)model.export(format="tensorrt")

CLI

libreyolo export model=LibreCenterNetresdcn18.pt format=onnx opset=18

Use the exported file

from libreyolo import LibreYOLO # The factory routes on the file suffix, so an exported artifact loads# like any checkpoint and returns the same Results object.model = LibreYOLO("LibreCenterNetresdcn18.onnx")result = model(SAMPLE_IMAGE) print(result.boxes.xyxy)

Checkpoints

Every published weight file for this family.

File	Input (px)	Weights license
Detection
LibreCenterNetresdcn18.pt	512	mit
LibreCenterNetdla34.pt	512	mit

Every file above exists in the LibreYOLO org today and downloads on first use.

Licensing

Check the license on the Hugging Face repository of the specific weights you download. Every checkpoint in the LibreYOLO org carries one, and they are not always the same across a family. That repository is the authoritative source; the summary below describes what applied when this page was last verified.

This is a description of the licenses involved, not legal advice. If the answer matters commercially, read the licenses yourself and take your own counsel.

Original work: CenterNet, UT Austin and UC Berkeley
Upstream license: MIT
Upstream source: github.com/xingyizhou/CenterNet
LibreYOLO code: MIT
Weights: MIT, republished at huggingface.co/LibreYOLO
Interpretation: MIT is a permissive license, so these weights can be used in commercial and closed-source products. It asks only that you keep the copyright notice and license text with any copy you redistribute, and it places no obligation on your own application code. The official ResDCN-18 and DLA-34 COCO checkpoints were published by the MIT-licensed CenterNet project but carry no separate per-checkpoint license file; LibreYOLO's mirror states MIT as implied by the releasing project rather than a publisher-confirmed, checkpoint-specific grant.

The ResDCN-18 graph also credits Microsoft's MIT-licensed human-pose-estimation.pytorch, and the DLA-34 graph credits Fisher Yu's BSD-3-Clause DLA implementation. LibreYOLO does not vendor the original DCNv2 extension the upstream project used; native execution runs torchvision's BSD-3-Clause deform_conv2d instead, and the export-only portable implementation was authored separately for LibreYOLO.

Citation

@inproceedings{zhou2019objects,
  title={Objects as Points},
  author={Zhou, Xingyi and Wang, Dequan and Kr{\"a}henb{\"u}hl, Philipp},
  booktitle={arXiv preprint arXiv:1904.07850},
  year={2019}
}

Copied from the authors' citation block at github.com/xingyizhou/CenterNet#citation.