Update server.py

server.py

@@ -18,7 +18,7 @@ import torchvision
 from torchvision import transforms as T
 from torchvision.transforms.functional import InterpolationMode
 
-# ---------------- basic config ----------------
+# basic config
 torch.set_num_threads(1)
 _INFER_LOCK = threading.Lock()
 
@@ -28,13 +28,13 @@ MAX_POINTS  = int(os.getenv("MAX_POINTS", "240"))
 
 FRESHNESS_NAMES = ["Fresh", "Spoiled"]
 
-# same as your notebook (no normalization)
+# preprocessing
 IMG_TX = T.Compose([
     T.Resize((224, 224), interpolation=InterpolationMode.BICUBIC),
     T.ToTensor()
 ])
 
-# ---------------- FastAPI ----------------
+# FastAPI
 app = FastAPI(title="Fruit Freshness & Gas Detector")
 app.add_middleware(
     CORSMiddleware,
@@ -44,12 +44,12 @@ app.add_middleware(
 LAST = {"vision": None, "vision_updated": None, "gas": None, "gas_updated": None}
 HISTORY = deque(maxlen=MAX_POINTS)
 
-# ---------------- model (same as notebook) ----------------
+# model
 class Model(nn.Module):
     def __init__(self):
         super().__init__()
         self.alpha = 0.7
-        # offline-safe: no download
+        
         try:
             self.base = torchvision.models.resnet18(weights=None)
         except TypeError:
@@ -129,7 +129,7 @@ def predict_pil(pil: Image.Image):
     raw = {FRESHNESS_NAMES[i]: float(p) for i, p in enumerate(probs_t)}
     return {"label": label, "confidence": round(conf, 1), "raw": {"probs": raw}}
 
-# ---------------- Vision ----------------
+# Vision
 @app.post("/predict")
 async def predict(image: UploadFile = File(...)):
     try:
@@ -146,7 +146,7 @@ async def predict(image: UploadFile = File(...)):
     except Exception as e:
         return JSONResponse({"error": "inference_failed", "detail": str(e)}, status_code=500)
 
-# ---------------- Gas ----------------
+# Gas 
 class GasReading(BaseModel):
     vrl: Optional[float] = None
     adc: Optional[int]   = None
@@ -234,14 +234,14 @@ def export_csv():
         headers={"Content-Disposition": 'attachment; filename="gas_history.csv"'}
     )
 
-# ---------------- Summary / Health ----------------
+# Summary / Health 
 def _summarize(last: dict) -> dict:
     """
     Combine the latest vision prediction and gas ppm into a single, simple decision.
     - Vision only votes 'rotten' if label says spoiled/rotten AND confidence >= VISION_MIN_CONF.
     - Any high gas flag can mark the sample as spoiled.
     """
-    # thresholds (tweak anytime)
+    # thresholds
     VISION_MIN_CONF = 60.0   # %
     CO2_HI  = 2000.0         # ppm
     NH3_HI  = 15.0           # ppm