Delete app.py

app.py

@@ -1,136 +0,0 @@
-import os
-import cv2
-import time
-import threading
-import numpy as np
-from datetime import datetime
-from fastapi import FastAPI, UploadFile, File
-from fastapi.staticfiles import StaticFiles
-from ultralytics import YOLO
-from PIL import Image
-
-# ==============================
-# ENV FIX (HF SAFE)
-# ==============================
-os.environ["YOLO_CONFIG_DIR"] = "/tmp/Ultralytics"
-os.environ["MPLCONFIGDIR"] = "/tmp/matplotlib"
-
-# ==============================
-# CONFIG
-# ==============================
-MODEL_PATH = "best.pt"
-OUTPUT_DIR = "/tmp/outputs"
-BASE_URL = "https://stroke-ia-detect-avc-image.hf.space"
-
-os.makedirs(OUTPUT_DIR, exist_ok=True)
-
-# ==============================
-# LOAD MODEL (ONCE)
-# ==============================
-print("🚀 Loading YOLO model...")
-model = YOLO(MODEL_PATH)
-print("✅ Model loaded")
-
-# ==============================
-# FASTAPI
-# ==============================
-app = FastAPI(title="Stroke-IA Facial Detection API")
-app.mount("/files", StaticFiles(directory=OUTPUT_DIR), name="files")
-
-# ==============================
-# UTILS
-# ==============================
-def generate_report(results) -> str:
-    boxes = results[0].boxes
-    if boxes is None or len(boxes) == 0:
-        return "=== RAPPORT AUTOMATIQUE ===\n\nAucune anomalie détectée.\n"
-
-    rapport = "=== RAPPORT AUTOMATIQUE AVC ===\n\n"
-    rapport += f"Nombre de signes détectés : {len(boxes)}\n\n"
-
-    for i, cls_id in enumerate(boxes.cls.cpu().numpy().astype(int), 1):
-        rapport += f"- Indice {i} : Classe {cls_id}\n"
-
-    rapport += "\n⚠️ Ce résultat est généré par une IA.\n"
-    rapport += "⚠️ Ne remplace pas un diagnostic médical.\n"
-
-    return rapport
-
-# ==============================
-# HEALTH CHECK (IMPORTANT)
-# ==============================
-@app.get("/health")
-def health():
-    return {
-        "status": "ok",
-        "model": "loaded",
-        "time": datetime.utcnow().isoformat()
-    }
-
-# ==============================
-# PREDICT
-# ==============================
-@app.post("/predict/")
-async def predict(image_file: UploadFile = File(...), conf: float = 0.8):
-
-    # ---------- Save temp image ----------
-    tmp_path = f"/tmp/{image_file.filename}"
-    with open(tmp_path, "wb") as f:
-        f.write(await image_file.read())
-
-    # ---------- Load image ----------
-    image = Image.open(tmp_path).convert("RGB")
-    np_img = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
-
-    # ---------- YOLO Prediction ----------
-    results = model.predict(
-        source=np_img,
-        conf=conf,
-        verbose=False
-    )
-
-    # ---------- No detection ----------
-    if results[0].boxes is None or len(results[0].boxes) == 0:
-        os.remove(tmp_path)
-        return {
-            "status": "ok",
-            "message": "✅ Aucun signe d’AVC détecté sur cette image."
-        }
-
-    # ---------- Annotate ----------
-    annotated = results[0].plot(labels=True)
-
-    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-    img_name = f"stroke_result_{timestamp}.png"
-    txt_name = f"rapport_{timestamp}.txt"
-
-    img_path = os.path.join(OUTPUT_DIR, img_name)
-    txt_path = os.path.join(OUTPUT_DIR, txt_name)
-
-    cv2.imwrite(img_path, annotated)
-
-    with open(txt_path, "w", encoding="utf-8") as f:
-        f.write(generate_report(results))
-
-    os.remove(tmp_path)
-
-    return {
-        "status": "success",
-        "annotated_result_url": f"{BASE_URL}/files/{img_name}",
-        "rapport_url": f"{BASE_URL}/files/{txt_name}",
-        "message": "⚠️ Signes potentiels détectés – Vérification médicale recommandée"
-    }
-
-# ==============================
-# AUTO CLEANUP
-# ==============================
-def cleanup(interval=600):
-    while True:
-        time.sleep(interval)
-        for f in os.listdir(OUTPUT_DIR):
-            try:
-                os.remove(os.path.join(OUTPUT_DIR, f))
-            except:
-                pass
-
-threading.Thread(target=cleanup, daemon=True).start()