Update app.py

app.py

@@ -1,6 +1,9 @@
 import os
+
+# 🔥 HARD CPU ENFORCEMENT (BEFORE ANY IMPORTS)
 os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
 os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
+os.environ["MEDIAPIPE_DISABLE_GPU"] = "1"
 
 import cv2
 import numpy as np
@@ -13,6 +16,7 @@ from cvzone.ClassificationModule import Classifier
 
 MODEL_PATH = "Model_old/keras_model.h5"
 LABELS_PATH = "Model_old/labels.txt"
+
 IMG_SIZE = 300
 OFFSET = 20
 CONFIDENCE_THRESHOLD = 0.5
@@ -22,13 +26,14 @@ STABILITY_THRESHOLD = 3
 
 app = Flask(__name__)
 
-# ---------------- MEDIAPIPE (CPU ONLY) ----------------
+# ---------------- MEDIAPIPE (CPU-ONLY, CLOUD SAFE) ----------------
 
 mp_hands = mp.solutions.hands
+
 hands = mp_hands.Hands(
-    static_image_mode=True,   # 🔥 REQUIRED for cloud
+    static_image_mode=True,     # REQUIRED for server inference
     max_num_hands=1,
-    model_complexity=0,       # 🔥 CPU-only
+    model_complexity=0,         # CPU graph only
     min_detection_confidence=0.6,
     min_tracking_confidence=0.6
 )
@@ -37,8 +42,8 @@ hands = mp_hands.Hands(
 
 classifier = Classifier(MODEL_PATH, LABELS_PATH)
 
-with open(LABELS_PATH) as f:
-    labels = [l.strip() for l in f.readlines()]
+with open(LABELS_PATH, "r") as f:
+    labels = [line.strip() for line in f.readlines()]
 
 stable_gesture = None
 stable_count = 0
@@ -52,19 +57,34 @@ def predict():
     if "frame" not in request.files:
         return jsonify({"gesture": None, "confidence": 0})
 
-    file = request.files["frame"]
-    img = np.frombuffer(file.read(), np.uint8)
-    frame = cv2.imdecode(img, cv2.IMREAD_COLOR)
-    frame = cv2.flip(frame, 1)
+    # ---- Decode image safely ----
+    try:
+        file = request.files["frame"]
+        img_bytes = np.frombuffer(file.read(), np.uint8)
+        frame = cv2.imdecode(img_bytes, cv2.IMREAD_COLOR)
+
+        if frame is None:
+            return jsonify({"gesture": None, "confidence": 0})
+
+        frame = cv2.flip(frame, 1)
+    except Exception:
+        return jsonify({"gesture": None, "confidence": 0})
 
-    rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-    result = hands.process(rgb)
+    # ---- MediaPipe inference ----
+    try:
+        rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        result = hands.process(rgb)
+    except Exception:
+        stable_gesture = None
+        stable_count = 0
+        return jsonify({"gesture": None, "confidence": 0})
 
     if not result.multi_hand_landmarks:
         stable_gesture = None
         stable_count = 0
         return jsonify({"gesture": None, "confidence": 0})
 
+    # ---- Bounding box from landmarks ----
     h, w, _ = frame.shape
     lm = result.multi_hand_landmarks[0].landmark
 
@@ -74,32 +94,53 @@ def predict():
     x, y = min(x_vals), min(y_vals)
     bw, bh = max(x_vals) - x, max(y_vals) - y
 
+    if bw <= 0 or bh <= 0:
+        return jsonify({"gesture": None, "confidence": 0})
+
+    # ---- Image preprocessing ----
     imgWhite = np.ones((IMG_SIZE, IMG_SIZE, 3), np.uint8) * 255
-    imgCrop = frame[max(0, y - OFFSET):y + bh + OFFSET,
-                    max(0, x - OFFSET):x + bw + OFFSET]
+
+    imgCrop = frame[
+        max(0, y - OFFSET): y + bh + OFFSET,
+        max(0, x - OFFSET): x + bw + OFFSET
+    ]
 
     if imgCrop.size == 0:
         return jsonify({"gesture": None, "confidence": 0})
 
     aspectRatio = bh / bw
 
-    if aspectRatio > 1:
-        k = IMG_SIZE / bh
-        wCal = math.ceil(k * bw)
-        imgResize = cv2.resize(imgCrop, (wCal, IMG_SIZE))
-        wGap = (IMG_SIZE - wCal) // 2
-        imgWhite[:, wGap:wGap + wCal] = imgResize
-    else:
-        k = IMG_SIZE / bw
-        hCal = math.ceil(k * bh)
-        imgResize = cv2.resize(imgCrop, (IMG_SIZE, hCal))
-        hGap = (IMG_SIZE - hCal) // 2
-        imgWhite[hGap:hGap + hCal, :] = imgResize
+    try:
+        if aspectRatio > 1:
+            k = IMG_SIZE / bh
+            wCal = max(1, math.ceil(k * bw))
+            imgResize = cv2.resize(imgCrop, (wCal, IMG_SIZE))
+            wGap = (IMG_SIZE - wCal) // 2
+            imgWhite[:, wGap:wGap + wCal] = imgResize
+        else:
+            k = IMG_SIZE / bw
+            hCal = max(1, math.ceil(k * bh))
+            imgResize = cv2.resize(imgCrop, (IMG_SIZE, hCal))
+            hGap = (IMG_SIZE - hCal) // 2
+            imgWhite[hGap:hGap + hCal, :] = imgResize
+    except Exception:
+        return jsonify({"gesture": None, "confidence": 0})
+
+    # ---- Classification ----
+    try:
+        prediction, index = classifier.getPrediction(imgWhite, draw=False)
+        index = int(index)
 
-    prediction, index = classifier.getPrediction(imgWhite, draw=False)
-    confidence = float(prediction[index])
-    gesture = labels[index]
+        if index < 0 or index >= len(labels):
+            return jsonify({"gesture": None, "confidence": 0})
 
+        confidence = float(prediction[index])
+        confidence = max(0.0, min(confidence, 1.0))
+        gesture = labels[index]
+    except Exception:
+        return jsonify({"gesture": None, "confidence": 0})
+
+    # ---- Stability logic ----
     if gesture == stable_gesture:
         stable_count += 1
     else:
@@ -112,4 +153,10 @@ def predict():
             "confidence": confidence
         })
 
-    return jsonify({"gesture": None, "confidence": 0})
+    return jsonify({"gesture": None, "confidence": 0})
+
+
+# ---------------- ENTRY ----------------
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)