Initial commit: Infrared Equipment Fault Detection HTTP Service

- Add FastAPI microservice for infrared equipment fault detection
- Add dual pyproject.toml: local development and Docker deployment
- Add MANUAL_SETUP.md for manual file placement instructions
- Add Dockerfile for containerized deployment
- Add sample .env.example for PROJECT_ROOT configuration
- Configure gitignore for weights, lib, venv, and environment files

.env.example

@@ -0,0 +1,2 @@
+# 项目根目录（修改为你的实际路径）
+PROJECT_ROOT=/path/to/Infrared-ai-inference-service

.gitignore

@@ -0,0 +1,53 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+*.egg
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+.tox/
+cov.xml
+*.cover
+*.log
+
+# Model weights
+weights/
+*.pt
+*.pth
+*.onnx
+*.ckpt
+
+# Lib (manually placed)
+lib/
+
+# Environment
+.python-version
+.venv/
+venv/
+.env
+.env.local
+
+# Lock files
+uv.lock
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Docker
+.dockerignore
+
+# Claude
+.claude/
+CLAUDE.md
+
+# Tests
+tests/

Dockerfile

@@ -0,0 +1,25 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# 安装 uv
+RUN pip install uv
+
+# 复制本地 whl 文件（预下载）
+COPY lib/ /app/lib/
+
+# 复制依赖配置（Docker 专用）
+COPY pyproject.docker.toml /app/pyproject.toml
+
+# 安装依赖（包括 infrared-data 从本地 whl）
+RUN uv pip install --system -r /app/pyproject.toml
+
+# 复制源码
+COPY src/ ./src/
+
+# 复制预下载的权重文件
+COPY weights/ /app/weights/
+
+EXPOSE 8000
+
+CMD ["python", "-m", "uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8000"]

MANUAL_SETUP.md

@@ -0,0 +1,58 @@
+# 手动部署说明
+
+由于网络限制，权重文件和 whl 包需要手动放置到本地目录。
+
+## 必需文件
+
+### 1. whl 包
+- **文件名**: `infrared_data-0.1.0-py3-none-any.whl`
+- **存放路径**: `lib/infrared_data-0.1.0-py3-none-any.whl`
+- **下载地址**: 联系项目维护者获取
+
+### 2. 模型权重文件
+- **文件名**: `best.pt`
+- **存放路径**: `weights/best.pt`
+- **下载地址**: 联系项目维护者获取
+
+## 目录结构
+
+```
+.
+├── lib/
+│   └── infrared_data-0.1.0-py3-none-any.whl
+├── weights/
+│   └── best.pt
+├── src/
+│   ├── __init__.py
+│   ├── config.py
+│   └── main.py
+├── tests/
+├── pyproject.toml
+└── Dockerfile
+```
+
+## 安装步骤
+
+```bash
+# 1. 放置上述文件到对应目录
+
+# 2. 创建 .env 文件（包含项目路径）
+#    注意：此文件包含绝对路径，每个开发者需要根据实际路径修改
+cp .env.example .env  # 或手动创建
+
+# 3. 创建虚拟环境并安装依赖
+set -a && source .env && uv sync
+
+# 4. 启动服务
+set -a && source .env && INFERENCE_DEVICE=cpu uv run uvicorn src.main:app --host 0.0.0.0 --port 8000
+```
+
+## 验证
+
+```bash
+# 健康检查
+curl http://localhost:8000/health
+
+# 测试推理
+curl -X POST http://localhost:8000/infer -F "image=@your_image.jpg"
+```

README.md

@@ -0,0 +1,148 @@
+# Infrared Equipment Fault Detection Service
+
+红外设备故障检测 HTTP 微服务，基于 `infrared-data` whl 包提供推理接口。
+
+## 功能特性
+
+- RESTful API 服务
+- 支持红外图像故障诊断
+- 返回检测框、温度特征、故障状态
+- CPU/GPU 灵活切换
+
+## 项目结构
+
+```
+.
+├── lib/                          # whl 包（需手动放置）
+│   └── infrared_data-0.1.0-py3-none-any.whl
+├── weights/                      # 模型权重（需手动放置）
+│   └── best.pt
+├── src/
+│   ├── __init__.py
+│   ├── config.py                 # 配置
+│   └── main.py                   # FastAPI 应用
+├── tests/
+│   └── valid/                    # 测试图片和结果
+├── pyproject.toml                # 本地依赖配置
+├── pyproject.docker.toml         # Docker 依赖配置
+├── Dockerfile                    # Docker 镜像
+├── MANUAL_SETUP.md               # 手动部署说明
+└── README.md                     # 本文件
+```
+
+## 快速开始
+
+### 1. 手动放置文件
+
+在部署前，需要手动获取并放置以下文件：
+
+| 文件 | 存放路径 |
+|------|----------|
+| whl 包 | `lib/infrared_data-0.1.0-py3-none-any.whl` |
+| 模型权重 | `weights/best.pt` |
+
+详细说明请参考 [MANUAL_SETUP.md](MANUAL_SETUP.md)。
+
+### 2. 安装依赖
+
+```bash
+uv sync
+```
+
+### 3. 启动服务
+
+```bash
+# CPU 模式
+INFERENCE_DEVICE=cpu uv run uvicorn src.main:app --host 0.0.0.0 --port 8000
+
+# GPU 模式
+INFERENCE_DEVICE=cuda:0 uv run uvicorn src.main:app --host 0.0.0.0 --port 8000
+```
+
+### 4. 测试
+
+```bash
+# 健康检查
+curl http://localhost:8000/health
+
+# 推理测试
+curl -X POST http://localhost:8000/infer -F "image=@your_image.jpg"
+```
+
+## API 文档
+
+启动服务后访问: http://localhost:8000/docs
+
+### POST /infer
+
+上传红外图像进行故障诊断。
+
+**请求**
+- Content-Type: `multipart/form-data`
+- 字段: `image` (图片文件)
+
+**响应**
+```json
+{
+  "image": "array",
+  "detections": [
+    {
+      "bbox": [x1, y1, x2, y2],
+      "bbox_xywh": [cx, cy, w, h],
+      "confidence": 0.94,
+      "class_id": 4,
+      "class_name": "conservator"
+    }
+  ],
+  "faults": [
+    {
+      "temp_max": 255.0,
+      "temp_min": 0.0,
+      "temp_mean": 81.1,
+      "temp_std": 68.3,
+      "temp_median": 57.0,
+      "fault_status": "abnormal",
+      "fault_type": "hotspot"
+    }
+  ],
+  "summary": {
+    "status": "fault_detected",
+    "detection_count": 3,
+    "abnormal_count": 3,
+    "fault_types": ["hotspot"]
+  }
+}
+```
+
+### GET /health
+
+健康检查接口。
+
+**响应**
+```json
+{
+  "status": "ok",
+  "device": "cpu"
+}
+```
+
+## Docker 部署
+
+```bash
+# 构建镜像
+docker build -t infrared-inference .
+
+# 运行容器
+docker run -p 8000:8000 infrared-inference
+```
+
+## 故障类型
+
+| 类型 | 说明 |
+|------|------|
+| `none` | 正常 |
+| `hotspot` | 热点异常 |
+| `local_overheating` | 局部过热 |
+| `overheat` | 过热 |
+| `suspect` | 可疑 |
+

pyproject.docker.toml

@@ -0,0 +1,12 @@
+[project]
+name = "infrared-inference"
+version = "0.1.0"
+description = "HTTP microservice for infrared equipment fault detection"
+requires-python = ">=3.10"
+dependencies = [
+    "fastapi>=0.115.0",
+    "uvicorn[standard]>=0.30.0",
+    "python-multipart>=0.0.12",
+    "aiofiles>=24.0.0",
+    "infrared-data @ file:///app/lib/infrared_data-0.1.0-py3-none-any.whl",
+]

pyproject.toml

@@ -0,0 +1,12 @@
+[project]
+name = "infrared-inference"
+version = "0.1.0"
+description = "HTTP microservice for infrared equipment fault detection"
+requires-python = ">=3.10"
+dependencies = [
+    "fastapi>=0.115.0",
+    "uvicorn[standard]>=0.30.0",
+    "python-multipart>=0.0.12",
+    "aiofiles>=24.0.0",
+    "infrared-data @ file://${PROJECT_ROOT}/lib/infrared_data-0.1.0-py3-none-any.whl",
+]

src/config.py

@@ -0,0 +1,19 @@
+import os
+from pathlib import Path
+
+# 权重文件地址
+WEIGHTS_URL = "http://193.112.94.100:9000/SkyLiCoder/Infrared-ai-research-lab/releases/download/v0.1.0/best.pt"
+
+# 权重本地路径
+WEIGHTS_DIR = Path(__file__).parent.parent / "weights"
+WEIGHTS_PATH = WEIGHTS_DIR / "best.pt"
+
+# whl 文件地址
+WHL_URL = "http://193.112.94.100:9000/SkyLiCoder/Infrared-ai-research-lab/releases/download/v0.1.0/infrared_data-0.1.0-py3-none-any.whl"
+
+# whl 本地路径
+WHL_DIR = Path(__file__).parent.parent / "lib"
+WHL_PATH = WHL_DIR / "infrared_data-0.1.0-py3-none-any.whl"
+
+# 推理设备: "cuda:0" / "cpu"
+DEVICE = os.getenv("INFERENCE_DEVICE", "cpu")

src/main.py

@@ -0,0 +1,66 @@
+import os
+import io
+from pathlib import Path
+from typing import Optional
+
+import numpy as np
+from fastapi import FastAPI, UploadFile, File, HTTPException
+from PIL import Image
+import uvicorn
+
+from infrared_data import FaultDiagnoser
+from src.config import WEIGHTS_PATH, DEVICE
+
+app = FastAPI(title="Infrared Equipment Fault Detection API")
+
+# 全局诊断器实例
+_diagnoser: Optional[FaultDiagnoser] = None
+
+
+def get_diagnoser() -> FaultDiagnoser:
+    global _diagnoser
+    if _diagnoser is None:
+        if not WEIGHTS_PATH.exists():
+            raise RuntimeError(
+                f"Weight file not found at {WEIGHTS_PATH}. "
+                "Please run: python scripts/download_assets.py"
+            )
+        _diagnoser = FaultDiagnoser(str(WEIGHTS_PATH))
+    return _diagnoser
+
+
+@app.post("/infer")
+async def infer(image: UploadFile = File(...)) -> dict:
+    """
+    接收一张红外图片，返回故障诊断结果（JSON）。
+
+    返回结构:
+    {
+        "image": str,
+        "detections": [...],
+        "faults": [...],
+        "summary": {
+            "status": str,
+            "detection_count": int,
+            "abnormal_count": int,
+            "fault_types": [...]
+        }
+    }
+    """
+    # 读取图片内容
+    contents = await image.read()
+    img = Image.open(io.BytesIO(contents)).convert("RGB")
+    img_array = np.array(img)
+
+    diagnoser = get_diagnoser()
+    result = diagnoser.diagnose(img_array, device=DEVICE)
+    return result
+
+
+@app.get("/health")
+async def health() -> dict:
+    return {"status": "ok", "device": DEVICE}
+
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8000)