FEAT: Add Dockerized FastAPI inference service

新增 FastAPI 人員存在偵測 API、模型載入服務與 uv 相依設定。\n加入 Dockerfile 與 Hugging Face Spaces 設定，並附上測試圖片。

.gitignore

@@ -0,0 +1,216 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

.python-version

@@ -0,0 +1 @@
+3.12

Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.12-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    UV_LINK_MODE=copy
+
+WORKDIR /app
+
+# Install system deps commonly needed by Pillow/torchvision runtime on Spaces.
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libglib2.0-0 \
+    libsm6 \
+    libxext6 \
+    libxrender1 \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN pip install --no-cache-dir uv
+
+COPY pyproject.toml uv.lock ./
+RUN uv sync --frozen --no-dev
+
+COPY . .
+
+EXPOSE 7860
+
+CMD ["sh", "-c", "uv run uvicorn app:app --host 0.0.0.0 --port ${PORT:-7860}"]

app.py

@@ -1,8 +1,56 @@
-import gradio as gr
+from contextlib import asynccontextmanager
+from io import BytesIO
 
-def greet(name):
-    return "Hello " + name + "!!"
+from fastapi import FastAPI, File, HTTPException, UploadFile
+from PIL import Image, UnidentifiedImageError
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+from model_service import MODEL_PATH, get_model_service
 
+
+@asynccontextmanager
+async def lifespan(_: FastAPI):
+    # Warm up model on startup so the first request is not slow.
+    get_model_service()
+    yield
+
+
+app = FastAPI(
+    title="Presence Detection API",
+    description="Detect whether an image contains a person.",
+    version="0.1.0",
+    lifespan=lifespan,
+)
+
+
+@app.get("/")
+def root():
+    return {
+        "message": "Presence Detection API",
+        "docs": "/docs",
+        "model_path": str(MODEL_PATH.name),
+    }
+
+
+@app.get("/health")
+def health():
+    return {"status": "ok", "model_loaded": True}
+
+
+@app.post("/predict")
+async def predict(file: UploadFile = File(...)):
+    if not file.content_type or not file.content_type.startswith("image/"):
+        raise HTTPException(status_code=400, detail="Uploaded file must be an image.")
+
+    data = await file.read()
+    if not data:
+        raise HTTPException(status_code=400, detail="Uploaded file is empty.")
+
+    try:
+        image = Image.open(BytesIO(data)).convert("RGB")
+    except UnidentifiedImageError as exc:
+        raise HTTPException(status_code=400, detail="Invalid image file.") from exc
+
+    result = get_model_service().predict_image(image)
+    result["filename"] = file.filename
+    result["content_type"] = file.content_type
+    return result

main.py

@@ -0,0 +1,31 @@
+from pathlib import Path
+from PIL import Image
+
+from model_service import MODEL_PATH, get_model_service
+
+
+IMAGE_PATH = Path("person.jpg")
+# IMAGE_PATH = Path("no_person.jpg")
+
+
+def main():
+    if not IMAGE_PATH.exists():
+        raise SystemExit(f"Image not found: {IMAGE_PATH}")
+
+    service = get_model_service()
+    print(f"[INFO] device={service.device}")
+    print(f"[INFO] model={MODEL_PATH}")
+    print(f"[INFO] image={IMAGE_PATH}")
+
+    img = Image.open(IMAGE_PATH).convert("RGB")
+    result = service.predict_image(img)
+
+    print("\n========== RESULT ==========")
+    print(f"Prediction: {result['label']}")
+    print(f"P(no_person) = {result['probabilities']['no_person']:.4f}")
+    print(f"P(person)    = {result['probabilities']['person']:.4f}")
+    print("============================")
+
+
+if __name__ == "__main__":
+    main()

model_service.py

@@ -0,0 +1,65 @@
+from functools import lru_cache
+from pathlib import Path
+
+import torch
+import torch.nn as nn
+import torchvision.transforms as T
+from PIL import Image
+from torchvision import models
+
+
+BASE_DIR = Path(__file__).resolve().parent
+MODEL_PATH = BASE_DIR / "best_global_model_presence.pt"
+CLASS_NAMES = ["no_person", "person"]
+
+
+def build_resnet18(num_classes: int = 2) -> nn.Module:
+    # We load task-specific weights from `best_global_model_presence.pt`, so no
+    # pretrained backbone download is needed at runtime.
+    model = models.resnet18(weights=None)
+    in_features = model.fc.in_features
+    model.fc = nn.Linear(in_features, num_classes)
+    return model
+
+
+class PresenceModelService:
+    def __init__(self, model_path: Path):
+        if not model_path.exists():
+            raise FileNotFoundError(f"Model not found: {model_path}")
+
+        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        self.model = build_resnet18(num_classes=2).to(self.device)
+
+        state = torch.load(model_path, map_location="cpu")
+        self.model.load_state_dict(state, strict=True)
+        self.model.eval()
+
+        self.transform = T.Compose(
+            [
+                T.Resize((224, 224)),
+                T.ToTensor(),
+                T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+            ]
+        )
+
+    def predict_image(self, image: Image.Image) -> dict:
+        x = self.transform(image).unsqueeze(0).to(self.device)
+
+        with torch.no_grad():
+            logits = self.model(x)
+            probs = torch.softmax(logits, dim=-1)[0]
+            pred_idx = int(torch.argmax(probs).item())
+
+        probabilities = {
+            CLASS_NAMES[i]: round(float(probs[i].item()), 6) for i in range(len(CLASS_NAMES))
+        }
+        return {
+            "label": CLASS_NAMES[pred_idx],
+            "prediction_index": pred_idx,
+            "probabilities": probabilities,
+        }
+
+
+@lru_cache(maxsize=1)
+def get_model_service() -> PresenceModelService:
+    return PresenceModelService(MODEL_PATH)

pyproject.toml

@@ -0,0 +1,21 @@
+[project]
+name = "securemlapi"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "fastapi>=0.133.1",
+    "uvicorn>=0.41.0",
+    "python-multipart>=0.0.20",
+    "matplotlib>=3.10.8",
+    "numpy>=2.4.2",
+    "opencv-python>=4.13.0.92",
+    "pandas>=3.0.1",
+    "pillow>=12.1.1",
+    "scikit-learn>=1.8.0",
+    "torch>=2.10.0",
+    "torchvision>=0.25.0",
+    "tqdm>=4.67.3",
+    "ultralytics>=8.4.17",
+]