libreyolo 1.3.1

Libre YOLO - An open source YOLO library with MIT license.

LibreYOLO

English | 简体中文

⭐ Support LibreYOLO. The best way to help is to star the repo. Feel free to open an issue if you encounter problems or have suggestions, and code contributions are very welcome (see CONTRIBUTING.md).

MIT-licensed computer vision library with inference and training support for a variety of models. It provides a familiar high-level Python and CLI interface and reads common YOLO-format datasets, so existing workflows port over with minimal changes.

Installation & Quick start

pip install libreyolo covers most users. It comes with the YOLOv9 flagship and the other detection models, plus training and inference. Now and then you'll add an extra: for a model family with a heavier dependency (for example RF-DETR, which needs the large transformers library), or for an export backend when you need to export a model:

pip install libreyolo

# Add an extra in brackets when you need one (comma-separate to combine),
# e.g. pip install "libreyolo[rfdetr,onnx]":
#   export:    onnx, tensorrt, openvino, ncnn, tflite, coreml
#   models:    rfdetr, vlm, sam, openvocab, clip, gaze
#   training:  lora, plots, tensorboard, mlflow, wandb
#   or all:    pip install "libreyolo[all]"

from libreyolo import LibreYOLO, SAMPLE_IMAGE

model = LibreYOLO("LibreYOLO9t.pt")
result = model(SAMPLE_IMAGE, save=True)

Image classification works the same way. Load a pretrained ImageNet-1k classifier (MobileNetV4, ConvNeXt, EfficientNetV2, or ResNet), then predict or fine-tune on your own folder-per-class dataset:

from libreyolo import LibreYOLO

model = LibreYOLO("LibreResNet50-cls.pt")   # weights auto-download on first use
result = model("image.jpg")                  # a single image -> one Results
print(result.probs.top1, float(result.probs.top1conf))  # class index + confidence
print(result.probs.top5)                     # indices of the 5 most likely classes

# Fine-tune on an ImageFolder dataset (train/ and val/, one sub-folder per
# class). The classifier head resizes to your class count automatically.
model.train(data="path/to/dataset", epochs=5)

For the full list of extras and per-backend notes, see the docs.

To install from source in editable mode (for development or to track unreleased changes):

git clone https://github.com/LibreYOLO/libreyolo.git
cd libreyolo
pip install -e .

Flagship models

LibreYOLO recommends these model families because they offer the best balance and receive the heaviest testing:

• YOLOv9 for CNN-based YOLO models.
• RF-DETR for transformer-based detection and segmentation.

Compatibility

✓ supported, exp experimental. Empty cells are not currently supported. All trainable families in the Training column accept universal training hooks via callbacks= and built-in experiment loggers via loggers= (tensorboard, mlflow, wandb).

Model family	Inference	Training	Export formats
Detection	Segmentation	Semantic	Classification	Pose	OBB	Gaze	ONNX	TorchScript	TensorRT	OpenVINO	NCNN	TFLite
⭐ YOLOv9	✓							✓	✓	✓	✓	✓	✓
⭐ RF-DETR	✓	✓	exp	exp	exp	exp		✓	✓	✓	✓	✓		exp
YOLOX	✓							exp	exp	exp	exp	exp	exp
YOLOv9-E2E	✓							exp	exp	exp	exp
YOLOv9-P2	✓							✓	exp
YOLO-NAS	✓				✓			exp	exp	exp	exp	exp	exp
D-FINE	✓							exp	exp	exp	exp	exp
DEIM	✓							exp	exp	exp	exp	exp
DEIMv2	✓							exp	exp	exp	exp	exp
RT-DETR	✓							exp	exp	exp	exp	exp
RT-DETRv2	✓							exp
RT-DETRv4	✓							exp
PicoDet	✓							exp	exp	exp
RTMDet	✓							exp
EC	✓	✓			✓			exp
MobileNetV4				✓				✓	✓
ConvNeXt				✓				✓	✓
EfficientNetV2				✓				✓	✓
ResNet				✓				✓	✓
L2CS							✓

YOLOv9-P2 is a small-object variant of YOLOv9 with an extra stride-4 detection scale, built for aerial/tiny-object imagery where objects fall below ~16 px (on regular datasets like COCO, prefer stock YOLOv9). A VisDrone-trained research preview is available as LibreYOLO9P2s-visdrone.pt (non-commercial license); train your own with LibreYOLO9P2(None, size="s").train(..., pretrained="LibreYOLO9s.pt").

License

• Code: MIT License
• Weights: Pre-trained weights may inherit licensing from the original source. Check the license in the specific HF repo of weights that you are interested in. LibreYOLO HF models always have a license.