initail commit

DockerFile

@@ -0,0 +1,31 @@
+# Use official Python slim image
+FROM python:3.11-slim
+
+# Set working dir
+WORKDIR /app
+
+# Install system deps needed for Pillow
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    libjpeg-dev \
+    zlib1g-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for better caching
+COPY requirements.txt /app/
+
+# Install python deps
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy app
+COPY . /app
+
+# Expose port (Spaces usually route; commonly 8080 works)
+EXPOSE 8080
+
+# Use a non-root user (optional but nice)
+RUN useradd --create-home appuser && chown -R appuser /app
+USER appuser
+
+# Run with Uvicorn
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080", "--workers", "1"]

main.py

@@ -0,0 +1,58 @@
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.responses import JSONResponse
+from pydantic import BaseModel
+from typing import Dict, Any
+from model import DummyGenderModel
+from PIL import Image
+import io
+import time
+import uuid
+
+app = FastAPI(title="Radiograph Gender Predictor (placeholder)",
+              description="Returns a random gender prediction for an uploaded radiograph image. Replace the DummyGenderModel with your trained model when ready.",
+              version="0.1.0")
+
+model = DummyGenderModel()  # placeholder. replace with your real model object when available.
+
+class PredictResponse(BaseModel):
+    id: str
+    prediction: str
+    confidence: float
+    probabilities: Dict[str, float]
+    model_version: str
+    runtime_ms: int
+    timestamp: float
+
+@app.get("/health")
+def health():
+    return {"status": "ok", "model_loaded": model.is_loaded(), "model_version": model.version}
+
+@app.post("/predict", response_model=PredictResponse)
+async def predict(file: UploadFile = File(...)):
+    """
+    Accepts an image file (radiograph). Returns a JSON with a random gender prediction.
+    Content-type should be one of common image types: image/jpeg, image/png, image/tiff, etc.
+    """
+    start = time.time()
+    # basic content-type check (optional)
+    if not file.content_type.startswith("image/"):
+        raise HTTPException(status_code=400, detail="Uploaded file must be an image.")
+
+    contents = await file.read()
+    try:
+        img = Image.open(io.BytesIO(contents)).convert("RGB")
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Unable to parse image: {e}")
+
+    # call the placeholder model (random)
+    result = model.predict(img)
+
+    runtime_ms = int((time.time() - start) * 1000)
+    response = {
+        "id": str(uuid.uuid4()),
+        "prediction": result["label"],
+        "model_version": model.version,
+        "runtime_ms": runtime_ms,
+        "timestamp": time.time()
+    }
+    return JSONResponse(content=response)

model.py

@@ -0,0 +1,51 @@
+"""
+Dummy model module.
+
+This file contains a placeholder model class `DummyGenderModel` that returns
+random predictions. Replace the `predict` method or the whole class with your
+trained model loading + inference logic when ready.
+"""
+
+import random
+from typing import Dict
+from PIL.Image import Image
+
+class DummyGenderModel:
+    def __init__(self):
+        self.version = "dummy-v0.1"
+        self._loaded = True
+
+    def is_loaded(self) -> bool:
+        return self._loaded
+
+    def predict(self, img: Image) -> Dict:
+        """
+        Return a random prediction. Expects a PIL Image.
+
+        Returns a dict:
+        {
+            "label": "male" or "female",
+            "confidence": float between 0.5 and 1.0,
+            "probabilities": {"male": p_male, "female": p_female}
+        }
+        """
+        # random base probability
+        p_male = random.random()
+        p_female = 1.0 - p_male
+
+        # calibrate to avoid extremely low confidences — push to [0.5, 1.0]
+        p_male = 0.5 + 0.5 * p_male
+        p_female = 1.0 - p_male
+
+        if p_male >= p_female:
+            label = "male"
+            # confidence = p_male
+        else:
+            label = "female"
+            # confidence = p_female
+
+        return {
+            "label": label,
+            # "confidence": round(confidence, 4),
+            # "probabilities": {"male": round(p_male, 4), "female": round(p_female, 4)}
+        }

requirement.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn[standard]
+pillow
+python-multipart