Update app.py

app.py

@@ -7,7 +7,7 @@ import pandas as pd
 from numpy.linalg import norm
 import matplotlib.pyplot as plt
 import os
-st.set_page_config(layout="wide")
+
 # Function to load the Random Forest model
 @st.cache_resource
 def load_model():
@@ -54,21 +54,35 @@ def calculate_angles(landmarks):
 
 # Function to process image and predict alphabet
 def process_and_predict(image):
-    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-    results = hands.process(image_rgb)
+    if image is None:
+        st.error("Failed to load the image. Please check if the file exists and is not corrupted.")
+        return None, None
+
+    try:
+        image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    except cv2.error:
+        st.error("Failed to convert the image. The image might be corrupted or in an unsupported format.")
+        return None, None
+
+    try:
+        results = hands.process(image_rgb)
+    except Exception as e:
+        st.error(f"An error occurred while processing the image: {str(e)}")
+        return None, None
+
+    if not results.multi_hand_landmarks:
+        st.warning("No hands detected in the image.")
+        return None, None
+
+    landmarks = np.array([[lm.x, lm.y] for lm in results.multi_hand_landmarks[0].landmark])
+    landmarks_normalized = normalize_landmarks(landmarks)
+    angles = calculate_angles(landmarks_normalized)
     
-    if results.multi_hand_landmarks:
-        landmarks = np.array([[lm.x, lm.y] for lm in results.multi_hand_landmarks[0].landmark])
-        landmarks_normalized = normalize_landmarks(landmarks)
-        angles = calculate_angles(landmarks_normalized)
-        
-        angle_columns = [f'angle_{i}' for i in range(len(angles))]
-        angles_df = pd.DataFrame([angles], columns=angle_columns)
-        
-        probabilities = model.predict_proba(angles_df)[0]
-        return probabilities, landmarks
+    angle_columns = [f'angle_{i}' for i in range(len(angles))]
+    angles_df = pd.DataFrame([angles], columns=angle_columns)
     
-    return None, None
+    probabilities = model.predict_proba(angles_df)[0]
+    return probabilities, landmarks
 
 # Function to plot hand landmarks
 def plot_hand_landmarks(landmarks, title):
@@ -85,8 +99,20 @@ def plot_hand_landmarks(landmarks, title):
     return fig
 
 # Streamlit app
+st.set_page_config(layout="wide")
 st.title("ASL Recognition App")
 
+# Debug information
+st.write("Current working directory:", os.getcwd())
+image_directory = 'asl test set'
+st.write("Image directory path:", os.path.abspath(image_directory))
+
+if os.path.exists(image_directory):
+    image_files = os.listdir(image_directory)
+    st.write("Files in the image directory:", image_files)
+else:
+    st.error(f"The directory '{image_directory}' does not exist.")
+
 # Create tabs for different functionalities
 tab1, tab2 = st.tabs(["Predict ASL Sign", "View Hand Landmarks"])
 
@@ -103,7 +129,7 @@ with tab1:
         with col2:
             probabilities, landmarks = process_and_predict(image)
             
-            if probabilities is not None:
+            if probabilities is not None and landmarks is not None:
                 st.subheader("Top 5 Predictions:")
                 top_indices = np.argsort(probabilities)[::-1][:5]
                 for i in top_indices:
@@ -111,8 +137,6 @@ with tab1:
                 
                 fig = plot_hand_landmarks(landmarks, "Detected Hand Landmarks")
                 st.pyplot(fig)
-            else:
-                st.write("No hand detected in the image.")
 
 with tab2:
     st.header("View Hand Landmarks")
@@ -126,17 +150,19 @@ with tab2:
         cols = st.columns(min(3, len(selected_alphabets)))
         for idx, alphabet in enumerate(selected_alphabets):
             with cols[idx % 3]:
-                image_path = f'asl test set/{alphabet.lower()}.jpeg'
+                image_path = os.path.join(image_directory, f'{alphabet.lower()}.jpeg')
+                st.write(f"Attempting to load: {image_path}")
                 if os.path.exists(image_path):
                     image = cv2.imread(image_path)
-                    _, landmarks = process_and_predict(image)
+                    if image is None:
+                        st.error(f"Failed to load image for {alphabet}. The file might be corrupted.")
+                        continue
+                    probabilities, landmarks = process_and_predict(image)
                     if landmarks is not None:
                         fig = plot_hand_landmarks(landmarks, f"Hand Landmarks for {alphabet}")
                         st.pyplot(fig)
-                    else:
-                        st.write(f"No hand detected for {alphabet}")
                 else:
-                    st.write(f"Image not found for {alphabet}")
+                    st.error(f"Image not found for {alphabet}")
 
 # Release MediaPipe resources
 hands.close()