---
title: ts_detector
canonical_url: "https://www.modelscope.cn/models/KeanuX/ts_detector"
md_url: "https://www.modelscope.cn/models/KeanuX/ts_detector.md"
repository: KeanuX/ts_detector
last_updated: 2025-12-24
license: "Apache License 2.0"
pipeline_tag: image-object-detection
tasks:
  - image-object-detection
model_type:
  - yolo
library_name:
  - pytorch
frameworks:
  - Pytorch
language:
  - python
domain:
  - cv
downloads: 2
stars: 0
tags:
  - pretrained
---

# ts_detector

> ts_detector - KeanuX 在 ModelScope 开源的模型。This is a model for traffic sign detection, which contains a total of 4 data labels: prohibition signs, danger signs, mandatory signs, and other signs.

KeanuX/ts_detector 是 ModelScope 魔搭社区上的image-object-detection模型，采用 Apache License 2.0 许可。

- **Repository**: KeanuX/ts_detector
- **License**: Apache License 2.0
- **Tasks**: image-object-detection
- **Tags**: pretrained
- **Downloads**: 2
- **Stars**: 0
- **Last updated**: 2025-12-24

Source: https://www.modelscope.cn/models/KeanuX/ts_detector

---

## 该模型使用Yolo预训练权重文件结合ts数据集进行模型训练

### 训练参数：

| Model   | epochs | batch | img-size | device | optimizer | lr_scheduler | lr   | classes |
| ------- | ------ | ----- | -------- | ------ | --------- | ------------ | ---- | ------- |
| YOLOV5m | 500    | 32    | 416      | cuda   | SGD       | LambdaLR     | 1e-2 | 4       |

### 训练结果：

| Class       | Images | Labels | P     | R     | mAP@.5 | mAP@.5:.95 |
| ----------- | ------ | ------ | ----- | ----- | ------ | ---------- |
| all         | 149    | 240    | 0.941 | 0.9   | 0.947  | 0.772      |
| prohibitory | 149    | 110    | 0.939 | 0.973 | 0.99   | 0.847      |
| danger      | 149    | 54     | 0.977 | 0.926 | 0.971  | 0.802      |
| mandatory   | 149    | 23     | 0.869 | 0.862 | 0.894  | 0.72       |
| other       | 149    | 53     | 0.978 | 0.838 | 0.935  | 0.721      |

#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

SDK下载

```bash
#安装ModelScope
pip install modelscope
```

```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('KeanuX/ts_detector')
```

Git下载

```
#Git模型下载
git clone https://www.modelscope.cn/KeanuX/ts_detector.git
```

<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>