Update app.py

app.py

@@ -1,8 +1,5 @@
 import cv2
-import mediapipe as mp
-
-from mediapipe.tasks.python import vision
-from mediapipe.tasks.python import BaseOptions
+import mediapipe.python.solutions.hands as mp_hands
 import numpy as np
 import torch
 import torch.nn as nn
@@ -12,12 +9,31 @@ import gradio as gr
 # Labels
 # ----------------------------
 GESTURE_LABELS = {
-    0: "A", 1: "B", 2: "L", 3: "U", 4: "V", 5: "W",
-    6: "Z", 7: "F", 8: "five", 9: "one", 10: "three",
-    11: "two", 12: "six", 13: "seven", 14: "eight",
-    15: "nine", 16: "ten", 17: "E", 18: "four",
-    19: "i", 20: "k", 21: "r", 22: "zero",
-    23: "m", 24: "s"
+    0: "A",
+    1: "B",
+    2: "L",
+    3: "U",
+    4: "V",
+    5: "W",
+    6: "Z",
+    7: "F",
+    8: "five",
+    9: "one",
+    10: "three",
+    11: "two",
+    12: "six",
+    13: "seven",
+    14: "eight",
+    15: "nine",
+    16: "ten",
+    17: "E",
+    18: "four",
+    19: "i",
+    20: "k",
+    21: "r",
+    22: "zero",
+    23: "m",
+    24: "s"
 }
 
 CONF_THRESHOLD = 0.6
@@ -28,76 +44,128 @@ CONF_THRESHOLD = 0.6
 class GestureNet(nn.Module):
     def __init__(self, input_size=126, num_classes=len(GESTURE_LABELS)):
         super().__init__()
+
         self.fc1 = nn.Linear(input_size, 256)
         self.fc2 = nn.Linear(256, 128)
         self.fc3 = nn.Linear(128, num_classes)
+
         self.relu = nn.ReLU()
         self.dropout = nn.Dropout(0.3)
 
     def forward(self, x):
         x = self.relu(self.fc1(x))
         x = self.dropout(x)
+
         x = self.relu(self.fc2(x))
         x = self.dropout(x)
-        return self.fc3(x)
 
+        x = self.fc3(x)
+
+        return x
+
+# ----------------------------
+# Load Model
+# ----------------------------
 model = GestureNet()
-model.load_state_dict(torch.load("gesture_model1.pth", map_location="cpu"))
+
+model.load_state_dict(
+    torch.load(
+        "gesture_model1.pth",
+        map_location=torch.device("cpu")
+    )
+)
+
 model.eval()
 
 # ----------------------------
-# MediaPipe
+# Prediction Function
 # ----------------------------
-mp_hands = mp.solutions.hands
-
 def predict(image):
-    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
 
-    with mp_hands.Hands(static_image_mode=True, max_num_hands=2) as hands:
-        results = hands.process(image)
+    if image is None:
+        return "No image uploaded"
+
+    # Convert RGB
+    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+    # MediaPipe Hands
+    with mp_hands.Hands(
+        static_image_mode=True,
+        max_num_hands=2,
+        min_detection_confidence=0.5
+    ) as hands:
+
+        results = hands.process(image_rgb)
 
     coords = []
 
+    # Extract landmarks
     if results.multi_hand_landmarks:
+
         for hand_landmarks in results.multi_hand_landmarks:
-            hand_coords = np.array([[lm.x, lm.y, lm.z] for lm in hand_landmarks.landmark])
 
+            hand_coords = np.array([
+                [lm.x, lm.y, lm.z]
+                for lm in hand_landmarks.landmark
+            ])
+
+            # Normalize
             hand_coords -= hand_coords[0]
-            max_val = np.max(np.linalg.norm(hand_coords, axis=1))
+
+            max_val = np.max(
+                np.linalg.norm(hand_coords, axis=1)
+            )
+
             if max_val > 0:
                 hand_coords /= max_val
 
             coords.extend(hand_coords.flatten())
 
+    # Pad / truncate
     if len(coords) < 126:
         coords.extend([0.0] * (126 - len(coords)))
+
     elif len(coords) > 126:
         coords = coords[:126]
 
-    if len(coords) == 126:
-        input_tensor = torch.tensor(coords, dtype=torch.float32).unsqueeze(0)
+    # Predict
+    input_tensor = torch.tensor(
+        coords,
+        dtype=torch.float32
+    ).unsqueeze(0)
+
+    with torch.no_grad():
 
-        with torch.no_grad():
-            outputs = model(input_tensor)
-            probs = torch.softmax(outputs, dim=1).numpy()[0]
+        outputs = model(input_tensor)
 
-        pred_class = np.argmax(probs)
-        confidence = probs[pred_class]
+        probs = torch.softmax(outputs, dim=1)
 
-        if confidence >= CONF_THRESHOLD:
-            return f"{GESTURE_LABELS[pred_class]} ({confidence*100:.2f}%)"
+        probs = probs.numpy()[0]
+
+    pred_class = np.argmax(probs)
+
+    confidence = probs[pred_class]
+
+    if confidence >= CONF_THRESHOLD:
+
+        label = GESTURE_LABELS[pred_class]
+
+        return f"{label} ({confidence * 100:.2f}%)"
 
     return "Unknown"
 
 # ----------------------------
-# Gradio UI
+# Gradio Interface
 # ----------------------------
 app = gr.Interface(
     fn=predict,
     inputs=gr.Image(type="numpy"),
     outputs="text",
     title="Hand Gesture Recognition",
-    description="Upload an image of a hand gesture"
+    description="Upload a hand gesture image"
 )
 
-app.launch()
+# ----------------------------
+# Launch
+# ----------------------------
+app.launch(server_name="0.0.0.0", server_port=7860)