Update app.py

app.py

@@ -1,7 +1,125 @@
-from fastapi import FastAPI
+import os
+import base64
+from typing import List, Dict, Any
+
+import numpy as np
+import cv2
+import requests
+from fastapi import FastAPI, File, UploadFile, HTTPException
+
+os.environ["KERAS_BACKEND"] = "jax"
+import keras
+
+# ─── Config ───────────────────────────────────────────────────────────────────
+API_KEY = os.environ["ROBOFLOW_API_KEY"]
+WORKFLOW_URL = "https://serverless.roboflow.com/YOUR_WORKSPACE/YOUR_WORKFLOW"  # adjust
+IMG_SIZE = 256
+THRESHOLD = 0.05  # ideally derived from healthy images [file:1]
+
+# ─── Load model once at startup ───────────────────────────────────────────────
+MODEL = keras.saving.load_model("hf://sairamv1/TeethCariesDetection_CNNAutoencoder")
 
 app = FastAPI()
 
-@app.get("/")
-def read_root():
-    return {"status": "Backend is running and waiting for model details!"}
+
+def first(seq):
+    """Return first element or None."""
+    return seq[0] if seq else None
+
+
+@app.post("/analyze")
+async def analyze(file: UploadFile = File(...)):
+    # ── Read & decode image ───────────────────────────────────────────────────
+    contents = await file.read()
+    nparr = np.frombuffer(contents, np.uint8)
+    img = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
+    if img is None:
+        raise HTTPException(status_code=400, detail="Invalid image file")
+
+    img_h, img_w = img.shape[:2]
+
+    # ── 1. Call Roboflow ──────────────────────────────────────────────────────
+    image_base64 = base64.b64encode(contents).decode("utf-8")
+    try:
+        response = requests.post(
+            WORKFLOW_URL,
+            json={
+                "api_key": API_KEY,
+                "inputs": {"image": {"type": "base64", "value": image_base64}},
+            },
+            timeout=60,
+        )
+        response.raise_for_status()
+    except requests.exceptions.Timeout:
+        raise HTTPException(status_code=504, detail="Roboflow request timed out")
+    except requests.exceptions.RequestException as e:
+        raise HTTPException(status_code=502, detail=f"Roboflow error: {e}")
+
+    result = response.json()
+    item0 = first(result)
+    if not item0:
+        return {"tooth_count": 0, "results": []}
+
+    outputs = first(item0.get("outputs", []))
+    pred_blob = outputs.get("predictions", {}) if outputs else {}
+    predictions_list: List[Dict[str, Any]] = (
+        pred_blob.get("predictions", []) if isinstance(pred_blob, dict) else (pred_blob or [])
+    )
+
+    if not predictions_list:
+        return {"tooth_count": 0, "results": []}
+
+    # ── 2. Prepare batch ──────────────────────────────────────────────────────
+    batch_images = []
+    metadata = []
+
+    for i, det in enumerate(predictions_list):
+        xc, yc, w, h = det["x"], det["y"], det["width"], det["height"]
+        x1 = max(0, int(round(xc - w / 2)))
+        y1 = max(0, int(round(yc - h / 2)))
+        x2 = min(img_w, int(round(xc + w / 2)))
+        y2 = min(img_h, int(round(yc + h / 2)))
+
+        crop = img[y1:y2, x1:x2]
+        if crop.size == 0:
+            continue
+
+        # Grayscale + CLAHE
+        gray = cv2.cvtColor(crop, cv2.COLOR_BGR2GRAY)
+        clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
+        gray = clahe.apply(gray)
+
+        # Resize with padding (preserve aspect ratio)
+        ch, cw = gray.shape[:2]
+        scale = IMG_SIZE / max(ch, cw)
+        new_w, new_h = max(1, int(round(cw * scale))), max(1, int(round(ch * scale)))
+        resized = cv2.resize(gray, (new_w, new_h), interpolation=cv2.INTER_AREA)
+
+        canvas = np.zeros((IMG_SIZE, IMG_SIZE), dtype=np.uint8)
+        y0, x0 = (IMG_SIZE - new_h) // 2, (IMG_SIZE - new_w) // 2
+        canvas[y0 : y0 + new_h, x0 : x0 + new_w] = resized
+
+        final_img = (canvas.astype(np.float32) / 255.0)[..., np.newaxis]
+        batch_images.append(final_img)
+        metadata.append({"id": i, "box": [x1, y1, x2, y2]})
+
+    if not batch_images:
+        return {"tooth_count": 0, "results": []}
+
+    # ── 3. Batch inference ────────────────────────────────────────────────────
+    batch_array = np.array(batch_images)  # (N, 256, 256, 1)
+    reconstructions = MODEL.predict(batch_array)
+
+    # ── 4. Anomaly scores ────────────────────────────────────────────────────���
+    errors = np.mean(np.abs(batch_array - reconstructions), axis=(1, 2, 3))
+
+    final_results = []
+    for idx, score in enumerate(errors):
+        final_results.append({
+            "tooth_index": metadata[idx]["id"],
+            "score": float(score),
+            "is_anomaly": bool(score > THRESHOLD),
+            "bounding_box": metadata[idx]["box"],
+        })
+
+    return {"tooth_count": len(final_results), "results": final_results}