Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ddm.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,107 @@
+import os
+from glob import glob
+import cv2
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from keras.utils import to_categorical
+from keras.models import load_model
+import streamlit as st
+
+# Define constants
+img_rows = 64
+img_cols = 64
+color_type = 1  # Grey
+NUMBER_CLASSES = 10
+
+# Load the saved model
+model = load_model('ddm.keras')
+
+# Define the get_cv2_image function
+def get_cv2_image(path, img_rows, img_cols, color_type=1):
+    """
+    Read and resize an image using OpenCV.
+    
+    Args:
+        path (str): Path to the image file.
+        img_rows (int): Desired number of rows for the resized image.
+        img_cols (int): Desired number of columns for the resized image.
+        color_type (int): Type of color space. Default is 1 (gray).
+        
+    Returns:
+        np.ndarray: Resized image array.
+    """
+    if color_type == 1:
+        img = cv2.imread(path, cv2.IMREAD_GRAYSCALE)
+    elif color_type == 3:
+        img = cv2.imread(path, cv2.IMREAD_COLOR)
+    else:
+        raise ValueError("Invalid color_type. Use 1 for grayscale or 3 for RGB.")
+    
+    img = cv2.resize(img, (img_rows, img_cols))
+    return img
+
+# Load dataset
+def load_test(size=200, img_rows=64, img_cols=64, color_type=1):
+    path = os.path.join(r"C:\Users\Gayathri Anil\Downloads\imgs\test", '*.jpg')
+    files = sorted(glob(path))
+    X_test, X_test_id = [], []
+    total = 0
+    files_size = len(files)
+    for file in files:
+        if total >= size or total >= files_size:
+            break
+        img = get_cv2_image(file, img_rows, img_cols, color_type)
+        X_test.append(img)
+        X_test_id.append(file)
+        total += 1
+    return X_test, X_test_id
+
+# Activity map
+activity_map = {'c0': 'Safe driving', 
+                'c1': 'Texting - right', 
+                'c2': 'Talking on the phone - right', 
+                'c3': 'Texting - left', 
+                'c4': 'Talking on the phone - left', 
+                'c5': 'Operating the radio', 
+                'c6': 'Drinking', 
+                'c7': 'Reaching behind', 
+                'c8': 'Hair and makeup', 
+                'c9': 'Talking to passenger'}
+
+# Streamlit app
+def main():
+    st.title('Driver Activity Recognition')
+    st.sidebar.title('Options')
+    
+    # Load and normalize sampled test data
+    test_files, _ = load_test()
+    
+    # Select an image
+    selected_image_index = st.sidebar.selectbox('Select an image:', range(len(test_files)))
+    selected_image = test_files[selected_image_index]
+    
+    # Display the selected image
+    st.image(selected_image, caption='Selected Image', use_column_width=True)
+    
+    # Classify the image
+    classify_button = st.sidebar.button('Classify')
+    if classify_button:
+        classify_image(selected_image)
+
+# Function to classify the image
+def classify_image(selected_image):
+    img_brute = cv2.resize(selected_image, (img_rows, img_cols))
+    
+    # Reshape the image
+    new_img = img_brute.reshape(-1, img_rows, img_cols, color_type)
+
+    # Predict the class label
+    y_prediction = model.predict(new_img)
+    predicted_class = np.argmax(y_prediction)
+    
+    # Display the prediction
+    st.write('Predicted class:', activity_map.get('c{}'.format(predicted_class)))
+
+if __name__ == '__main__':
+    main()

ddm.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9015fc4de6e7eeab204f187fd42b1cb6d2343d246c1c50216ea487f1d492b2f
+size 36509330