Instructions to use dkrak737/battery-ct-defect-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use dkrak737/battery-ct-defect-models with ultralytics:
# Couldn't find a valid YOLO version tag. # Replace XX with the correct version. from ultralytics import YOLOvXX model = YOLOvXX.from_pretrained("dkrak737/battery-ct-defect-models") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: ultralytics
|
| 4 |
+
tags: [yolo, ultralytics, battery, ct, defect-detection, segmentation, classification]
|
| 5 |
+
---
|
| 6 |
+
# 배터리 CT 내부결함 탐지 — 가중치
|
| 7 |
+
|
| 8 |
+
기내 화재(내부 단락) 예방용 배터리 CT 결함 스크리닝 모델 묶음. recall 우선.
|
| 9 |
+
|
| 10 |
+
| 파일 | task | 결함 | 비고 |
|
| 11 |
+
|---|---|---|---|
|
| 12 |
+
| `module_r01c.pt` | detect | porosity, resin overflow | module pouch, imgsz 512, conf 0.05 |
|
| 13 |
+
| `cell_r06.pt` | detect | porosity | cell pouch, imgsz 640, 검토 큐 |
|
| 14 |
+
| `swell_kf0~4.pt` | classify | swelling | 5-fold 앙상블, normal=0/swelling=1, imgsz 224 |
|
| 15 |
+
| `porosity_best.pt` | segment | porosity | 정밀 마스크, cell 4x 타일 |
|
| 16 |
+
|
| 17 |
+
데모/코드: https://github.com/dkrak737-svg/battery-ct-defect-screening
|
| 18 |
+
데이터: AI-Hub 103.배터리 불량 이미지(71687), CT만. 원본 미배포(약관).
|