Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- image-classification
|
| 5 |
+
- image-segmentation
|
| 6 |
+
- defect-detection
|
| 7 |
+
- pytorch
|
| 8 |
+
- unet++
|
| 9 |
+
- resnet
|
| 10 |
+
- dqn
|
| 11 |
+
language:
|
| 12 |
+
- zh
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# 汽车漆面缺陷检测模型
|
| 16 |
+
|
| 17 |
+
基于深度学习的汽车漆面缺陷检测系统，包含三个核心模块。
|
| 18 |
+
|
| 19 |
+
## 模型文件
|
| 20 |
+
|
| 21 |
+
| 模型 | 文件 | 大小 | 用途 |
|
| 22 |
+
|------|------|------|------|
|
| 23 |
+
| DQN图像增强 | task1_dqn/dqn_final.pth | ~987MB | 强化学习图像增强 |
|
| 24 |
+
| UNet++分割 | task2_unetpp/best_model.pth | ~105MB | 缺陷区域分割 (IoU=0.884) |
|
| 25 |
+
| ResNet分类 | task3_classification/best_model.pth | ~283MB | 缺陷类型分类 (Acc=96.3%) |
|
| 26 |
+
|
| 27 |
+
## 下载方法
|
| 28 |
+
|
| 29 |
+
```python
|
| 30 |
+
from huggingface_hub import hf_hub_download
|
| 31 |
+
|
| 32 |
+
# 下载分割模型
|
| 33 |
+
model_path = hf_hub_download(
|
| 34 |
+
repo_id="TrainingCat/car-paint-defect-detection",
|
| 35 |
+
filename="task2_unetpp/best_model.pth"
|
| 36 |
+
)
|
| 37 |
+
```
|
| 38 |
+
|
| 39 |
+
或使用命令行:
|
| 40 |
+
|
| 41 |
+
```bash
|
| 42 |
+
huggingface-cli download TrainingCat/car-paint-defect-detection --local-dir models/
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
## 数据集
|
| 46 |
+
|
| 47 |
+
[Roboflow Car Paint Defect Dataset](https://universe.roboflow.com/poli-h7nww/final-year-car-paint-defect/dataset/1)
|