---
title: MolDetv2-YOLO26
canonical_url: "https://www.modelscope.cn/models/UniParser/MolDetv2-YOLO26"
md_url: "https://www.modelscope.cn/models/UniParser/MolDetv2-YOLO26.md"
repository: UniParser/MolDetv2-YOLO26
last_updated: 2026-09-09
license: cc-by-nc-sa-4.0
base_model:
  - Ultralytics/YOLO26
base_model_relation: finetune
library_name:
  - onnx
  - pytorch
frameworks:
  - pytorch
downloads: 22
stars: 0
tags:
  - chemistry
---

# MolDetv2-YOLO26

> MolDetv2-YOLO26 - UniParser 在 ModelScope 开源的模型。MolDetv2 (YOLO26 Version)

UniParser/MolDetv2-YOLO26 是 ModelScope 魔搭社区上的机器学习模型，采用 cc-by-nc-sa-4.0 许可，基于 Ultralytics/YOLO26 构建。

- **Repository**: UniParser/MolDetv2-YOLO26
- **License**: cc-by-nc-sa-4.0
- **Base model**: Ultralytics/YOLO26
- **Tags**: chemistry
- **Downloads**: 22
- **Stars**: 0
- **Last updated**: 2026-09-09

Source: https://www.modelscope.cn/models/UniParser/MolDetv2-YOLO26

---

# MolDetv2 (YOLO26 Version)

This repository provides the **YOLO26-based version** of [MolDetv2](https://huggingface.co/UniParser/MolDetv2) model.


## 💻 Usage

Detect molecules in an image:
```
from ultralytics import YOLO
model = YOLO("/path/to/moldet_v2_yolo26n_640_general.pt")  # for cpu only inference: using `moldet_v2_yolo26n_640_general.onnx` for faster speed
model.predict("path/to/image.png", save=True, imgsz=640, conf=0.5)
```

Detect molecules in a PDF document:
```
from ultralytics import YOLO
import fitz # MuPDF
pdf = fitz.open("doc.pdf")
model = YOLO("/path/to/moldet_v2_yolo26n_960_doc.pt")  # for cpu only inference: using `moldet_v2_yolo26n_960_doc.onnx` for faster speed
bboxes = []
for i, p in enumerate(pdf):
    img = f"page_{i}.png"; p.get_pixmap().save(img)
    for r in model.predict(img, imgsz=960, conf=0.5):
        for box in r.boxes:
            bboxes.append({"page":img, "conf":float(box.conf), "bbox":box.xyxy[0].tolist()})

```

## 📜 License

MolDet & MolDetv2 model weights are provided for **non-commercial use only**. 

For commercial use, please contact: [fangxi@dp.tech](mailto:fangxi@dp.tech) or add a discussion in HuggingFace.


## 📖 Citation

If you use this model in your work, please cite:

```
@article{fang2026molparserm,
  title={MolParser-Mobile: Ultrafast OCSR System for Large-Scale Chemical Literature Mining},
  author={Fang, Xi and Lu, Haocheng and Lyu, Han and Luo, Chengxiang and Zhang, Linfeng and Ke, Guolin},
  journal={arXiv preprint arXiv:2609.05807},
  year={2026}
}
```