TinyFormer

TinyFormer is a trainable transformer detector with a DINOv3 backbone.

Task
detection
Instalasi
pip install libreyolo
Tier dukungan
Inti, sejak v1.6.0. Detektor inti yang dapat dilatih: fitur menyusul tier unggulan dalam gelombang rilis yang sama.
Proyek upstream
TinyFormer oleh TinyFormer authors, Apache-2.0; DINOv3 terms. Makalah, sumber
Lisensi
Kode MIT, bobot Apache-2.0; DINOv3 terms. Penggunaan komersial

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

TaskONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNncnnTFLiteCoreMLCore AI
DetectionDetection to ONNX: didukungDetection to TorchScript: didukungDetection to ExecuTorch: didukungDetection to TensorRT: didukungDetection to OpenVINO: didukungDetection to Paddle: tidak didukungDetection to MNN: tidak didukungDetection to RKNN: tidak didukungDetection to ncnn: tidak didukungDetection to TFLite: tidak didukungDetection to CoreML: tidak didukungDetection to Core AI: tidak didukung
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

Tensorimages float32 [batch, 3, height, width]
WarnaRGB
Penskalaanpiksel / 255
Normalisasirata-rata [0.485,0.456,0.406], simpangan baku [0.229,0.224,0.225]
Ubah ukuranregangkan ke lebar x tinggi (tanpa padding, rasio aspek tidak dipertahankan), Pillow bilinear
Cara mereproduksi resize bilinear Pillow

LibreYOLO mengubah ukuran dengan filter BILINEAR milik Pillow (Image.resize). Ini bukan OpenCV INTER_LINEAR maupun INTER_AREA: saat memperkecil, Pillow memperlebar filter sebesar faktor pengecilan, dan resize OpenCV mengubah deteksi serta menggeser kotak beberapa piksel. Untuk mereproduksinya tanpa Pillow, ubah ukuran satu sumbu, bulatkan ke 8 bit, lalu ubah ukuran sumbu lainnya dan bulatkan lagi. Per sumbu, misalkan s = in_size / out_size dan f = max(s, 1). Piksel keluaran i berpusat di c = (i + 0.5) * s dan membaca piksel sumber j dari int(c - f + 0.5) sampai int(c + f + 0.5) - 1, dibatasi pada gambar, masing-masing dengan bobot max(0, 1 - |j + 0.5 - c| / f), dibagi jumlah bobot. Pillow bekerja dengan fixed point dan memilih urutan sumbu dari bentuk gambar, sehingga bobot float dapat berbeda satu level pada beberapa piksel. Hal itu tidak mengubah hasil pada pemeriksaan kami.

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, ekspor default
OutputBentukArti
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.

Pascapemrosesan

  1. Apply sigmoid to pred_logits.
  2. 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.
  3. Keep the pairs whose score is above the confidence threshold (0.25 by default).
  4. 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.
  5. There is no NMS and the iou threshold is not used. TinyFormer predicts a set of boxes, and export with nms=True raises NotImplementedError.
  6. LibreYOLO does not clip these boxes, so an edge can sit slightly outside the image.

Untuk memeriksa implementasi Anda sendiri, jalankan file yang sama lewat LibreYOLO: LibreYOLO("model.onnx").predict("image.jpg") mengembalikan hasil acuan. Diverifikasi dengan LibreYOLO 1.7.0.

Checkpoints

Licensing

Periksa lisensi di repositori Hugging Face untuk bobot tertentu yang diunduh. Setiap checkpoint di organisasi LibreYOLO memiliki lisensi, dan lisensinya tidak selalu sama dalam satu family. Repositori tersebut adalah sumber resmi. Ringkasan di bawah menjelaskan ketentuan yang berlaku saat halaman ini terakhir diverifikasi.

Ini adalah deskripsi lisensi yang terlibat, bukan nasihat hukum. Jika jawabannya penting secara komersial, baca sendiri lisensinya dan mintalah nasihat dari penasihat hukum Anda.

Karya asli
TinyFormer, TinyFormer authors
Lisensi upstream
Apache-2.0; DINOv3 terms
Kode LibreYOLO
MIT
Bobot
Apache-2.0; DINOv3 terms, dipublikasikan ulang di huggingface.co/LibreYOLO
Interpretasi
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}

}

Disalin dari blok sitasi penulis di raw.githubusercontent.com/mmpmmpmmpjosh/TinyFormer/main/README.md.

Diverifikasi dengan LibreYOLO v1.6.0. Tabel dukungan, checkpoint, dan angka benchmark di halaman ini dihasilkan dari library yang telah dirilis dan bobot yang dipublikasikan, bukan ditulis manual.