greatkoko/tank-nationality-identification-YOLO26s
object-detection model by greatkoko
Older snapshot: check the original source for current information.
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.
Detects main battle tanks and classifies their nationality into 4 classes. The model was re-trained with Ultralytics YOLO26s on the dataset of which used YOLOv4 (Darknet). This release re-evaluates the same task with a modern detector and a stricter, leakage-free test protocol. (1,500 per class; 1,494 for southkorea) so near-duplicates never appear in both training and test data The paper's numbers come from a random validation split (noise versions of the same photo may appear in training) and Darknet's AP computation, so the comparison is indicative rather than exact. 0.995 is the upper bound of Ultralytics' interpolated AP. southkorea is the hardest class for both models. Friend = usa, southkorea; foe = northkorea. Recommended operating threshold: conf = 0.7. On this test set all friend/foe confusions disappear at conf ≥ 0.7, while recall drops only from 0.986 to 0.981 and precision rises from 0.988 to 0.997. Above 0.75 recall falls…
Read the full model card ↗ · Preview checked 2026-10-29T23:51:21.627Z
Inside the original model card — Document outline
- Tank Nationality Identification — YOLO26s
- Files
- Data
- Results
- Held-out test set (897 images, imgsz 640)
- Identification-friend-or-foe view (test set)
- By noise condition (test set)
- Deployment benchmark (300 test images, batch 1)
- Usage
- Training
- Limitations
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
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
greatkoko/tank-nationality-identification-YOLO26s is a object-detection model repository published by greatkoko 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)
- 0
- 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
- 2026-10-25T06:14:43.000Z
- Last modified
- 2026-10-25T06:26:00.000Z
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 2026-10-25T06:46:38.979Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
mudler/locate-anything.cpp-gguf
microsoft/table-transformer-structure-recognition
PekingU/rtdetr_r101vd_coco_o365