TinyFormer

TinyFormer is a trainable transformer detector with a DINOv3 backbone.

任务: detection
安装: pip install libreyolo
支持层级: 核心，自 v1.6.0 起。核心的可训练检测器：功能在同一个发布波次里紧跟旗舰。
上游: TinyFormer，由 TinyFormer authors 发布，采用 Apache-2.0; DINOv3 terms 许可。论文、源码
许可: 代码采用 MIT，权重采用 Apache-2.0; DINOv3 terms。商用

Install

bash

pip install "libreyolo"

Predict

Python

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreTinyFormers.pt", device="cpu")result = model(SAMPLE_IMAGE)print(result)

Choose a published checkpoint below. The naming distinguishes the VisDrone variants and Objects365-to-COCO variants. Prediction requires a square imgsz; rectangular inputs raise an error.

Train

Training accepts a detection dataset YAML. Omitted epochs, batch, imgsz, lr0 and amp use the family recipe.

Dataset setup describes the required training data.

Python

from libreyolo import LibreYOLO model = LibreYOLO("LibreTinyFormers.pt", device="cpu")# coco8.yaml is a built-in 8-image detection dataset that downloads on first use.# Replace it with the path to your own detection dataset YAML.model.train(data="coco8.yaml", epochs=1, device="cpu", workers=0)

Validate

Python

from libreyolo import LibreYOLO model = LibreYOLO("LibreTinyFormers.pt", device="cpu")# coco8.yaml downloads on first use; pass your own detection dataset YAML instead.metrics = model.val(data="coco8.yaml", workers=0)print(metrics)

Use the dataset format for this task. Validation explains the dataset requirements and returned metrics.

Export

任务	ONNX	TorchScript	ExecuTorch	TensorRT	OpenVINO	Paddle	MNN	RKNN	ncnn	TFLite	CoreML	Core AI
Detection	Detection to ONNX：支持	Detection to TorchScript：支持	Detection to ExecuTorch：支持	Detection to TensorRT：支持	Detection to OpenVINO：支持	Detection to Paddle：不支持	Detection to MNN：不支持	Detection to RKNN：不支持	Detection to ncnn：不支持	Detection to TFLite：不支持	Detection to CoreML：不支持	Detection to Core AI：不支持

Python

from libreyolo import LibreYOLO, SAMPLE_IMAGE model = LibreYOLO("LibreTinyFormers.pt", device="cpu")model.export(format="onnx")

Export setup lists format dependencies and loading exported artifacts.

ONNX inputs and outputs

张量	`images` `float32` `[batch, 3, height, width]`
颜色	RGB
缩放	像素 / 255
归一化	均值 [0.485,0.456,0.406], 标准差 [0.229,0.224,0.225]
缩放方式	拉伸到宽 x 高(不填充,不保持宽高比), Pillow bilinear

如何复现 Pillow 的双线性缩放

LibreYOLO 使用 Pillow 的 BILINEAR 滤波器(Image.resize)缩放。它不是 OpenCV 的 INTER_LINEAR 或 INTER_AREA:缩小时,Pillow 会按缩小倍数加宽滤波器,而 OpenCV 的缩放会改变检测结果,并使框移动数个像素。要在不使用 Pillow 的情况下复现它,先缩放一个轴,舍入到 8 位,再缩放另一个轴并再次舍入。对每个轴,令 s = in_size / out_size,f = max(s, 1)。输出像素 i 的中心为 c = (i + 0.5) * s,读取源像素 j,范围从 int(c - f + 0.5) 到 int(c + f + 0.5) - 1(限制在图像内),每个像素的权重为 max(0, 1 - |j + 0.5 - c| / f),再除以权重之和。Pillow 使用定点运算,并根据图像形状选择轴的顺序,因此浮点权重在少数像素上可能与它相差一个等级。这不会改变我们检查中的结果。

Square input only. Export rejects a non-square imgsz, and height and width are 640 by default for every size. Another square imgsz must be a multiple of 32.

Batch size 1 only. The graph declares a dynamic batch axis, but batches of 2 or more fail in 1.7.0.

After the resize, divide by 255, then subtract the ImageNet mean and divide by the ImageNet std, per channel in RGB order.

Detection，默认导出

输出	形状	含义
`pred_logits`	`[batch, queries, nc]`	One logit per query and class. Sigmoid is not applied. queries is 300 for every size.
`pred_boxes`	`[batch, queries, 4]`	cx, cy, w, h of each query, normalized 0 to 1 of the input. The input is the whole image stretched, so these are also fractions of the original image.

后处理

Apply sigmoid to pred_logits.
Flatten the [queries, nc] scores and take the top 300 (max_det, 300 by default). For flat index k, the query is k // nc and the class is k % nc. One query can yield several classes.
Keep the pairs whose score is above the confidence threshold (0.25 by default).
Convert the query's box to x1 = cx - w / 2, y1 = cy - h / 2, x2 = cx + w / 2, y2 = cy + h / 2. Multiply x by the original image width and y by the original image height.
There is no NMS and the iou threshold is not used. TinyFormer predicts a set of boxes, and export with nms=True raises NotImplementedError.
LibreYOLO does not clip these boxes, so an edge can sit slightly outside the image.

要检查你自己的实现，请用 LibreYOLO 运行同一个文件：LibreYOLO("model.onnx").predict("image.jpg") 会返回参考结果。已用 LibreYOLO 1.7.0 验证。

Checkpoints

文件	权重许可
Detection
LibreTinyFormers.pt	other
LibreTinyFormerm.pt	other
LibreTinyFormerl.pt	other
LibreTinyFormerx.pt	other
LibreTinyFormerxl.pt	other
LibreTinyFormers-visdrone.pt	other
LibreTinyFormerm-visdrone.pt	other
LibreTinyFormerl-visdrone.pt	other
LibreTinyFormerx-visdrone.pt	other
LibreTinyFormerx-obj2coco.pt	other
LibreTinyFormerxl-obj2coco.pt	other

上面的每个文件目前都在 LibreYOLO 组织中，并会在首次使用时下载。

Licensing

请检查你所下载的具体权重在 Hugging Face 仓库中的许可。LibreYOLO 组织里的每个检查点都附有许可，同一家族内也不一定相同。该仓库是权威来源；以下摘要说明本页上次验证时适用的情况。

这里只说明涉及的许可证，不构成法律意见。如果答案对商用很重要，请自行阅读许可证并咨询法律顾问。

原始工作: TinyFormer, TinyFormer authors
上游许可: Apache-2.0; DINOv3 terms
上游来源: github.com/mmpmmpmmpjosh/TinyFormer
LibreYOLO 代码: MIT
权重: 采用 Apache-2.0; DINOv3 terms 许可，重新发布在 huggingface.co/LibreYOLO
解读: The detector uses Apache-2.0 source and a DINOv3 backbone with its own terms. Check the publisher declarations for the chosen checkpoint.

Citation

@article{hsieh2026tinyformer,

  title={TinyFormer: Preserving Tiny Objects in YOLO-DETR Hybrid Real-time Detectors},

  author={Hsieh, Jun-Wei and Kao, Meng-Yu and Kurniawan, Ghufron Wahyu and Peng, Kuan-Chuan},

  journal={arXiv preprint arXiv:2605.25046},

  year={2026}

}

复制自作者在 raw.githubusercontent.com/mmpmmpmmpjosh/TinyFormer/main/README.md 上提供的引用块。