p4ulbr4dl3y/eskd-yolo26
object-detection model by p4ulbr4dl3y
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Детекторы YOLO26s для синтетических и реальных чертежей ЕСКД/ГОСТ. Модель размечает геометрию: рамку, штамп, ячейки, зоны видов, текст как области, стрелки и символы. Текст не распознаётся. Метрики — синтетический test, 400 листов. Это не оценка на реальных сканах. Проверка на реальных веб-листах (54 листа после автофильтра, conf≥0.25): детекции на 53 листах, 4011 объектов, медиана уверенности 0.849, найдены все 20 классов. Это покрытие, а не качество: эталонной разметки нет, precision и recall на реальных данных не измерялись. Сильнее всего проседают мелкие знаки и ячейки: datumletter 0.853, sectionmark 0.854, gdtdatum 0.861, deviation 0.869, bomcell 0.889 (mAP50-95). Лучшие — holecallout 0.978, dimensionnote 0.974, roughness 0.972. Текст детектируется как область, содержимое не распознаётся. 44 области на чистом листе при conf≥0.4; легенда классов — внизу изображения. Лист из test-сплита: слева оригинал, справа предсказание layout, 12 объектов, min conf 0.96. Штамп крупным…
Read the full model card ↗ · Preview checked 2026-11-17T07:08:08.125Z
Inside the original model card — Document outline
- ESKD vision — модель
- Задачи
- text: качество по классам
- Веса
- Инференс
- Реальные снимки
- Обучение
- Ограничения
- Данные
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: agpl-3.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
p4ulbr4dl3y/eskd-yolo26 is a object-detection model repository published by p4ulbr4dl3y on Hugging Face. The source reports the ultralytics library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- object-detection
- Library
- ultralytics
- Recent downloads (30 days)
- 9,622
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- agpl-3.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-15T00:11:23.000Z
- Last modified
- 2026-11-16T09:57:05.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-17T07:06:10.815Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
microsoft/table-transformer-structure-recognition
PekingU/rtdetr_r101vd_coco_o365
PaddlePaddle/PP-DocLayoutV3_safetensors