Update RESNET_images.py

RESNET_images.py

@@ -1,272 +1,209 @@
-# -*- coding: utf-8 -*-
-#images- 2800 training, test- 280
-# 10 epoch, batch= 32, kfold= 4
-# test accuracy 0.75
-# test loss 1.26
-# avarage accuracy 61.84
-#Classification Summary:
-#Real images correctly classified: 76
-#Real images incorrectly classified: 63
-#Fake images correctly classified: 135
-#Fake images incorrectly classified: 5
-###########resnet- מקפיא חלק מהשכבות ההתחלתיות כלומר יש אימון על שכבות רבות##########
-#resnet_model = tf.keras.applications.ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
-# Freeze initial layers (optional)
-#for layer in resnet_model.layers[:17]:<<<<=
-#    layer.trainable = False
-# Modify final layer
-#x = resnet_model.output
-#x = tf.keras.layers.Flatten()(x)
-#x = tf.keras.layers.Dense(64, activation='relu')(x)<<<<<<=
-#predictions = tf.keras.layers.Dense(1, activation='sigmoid')(x)  # Binary classification
-
-
-
-##images- 2800 training, test- 280
-#KFold(n_splits=4, batch_size = 32, epochs = 5
-#train only last layer
-#Classification Summary:
-#Average accuracy: 76.95%
-#Test Loss: 0.4741879999637604, Test Accuracy: 0.781361997127533
-#Real images correctly classified: 116
-#Real images incorrectly classified: 23
-#Fake images correctly classified: 102
-#Fake images incorrectly classified: 38
-
-#############
-#saves weight
-##images- 2800 training, test- 280
-#KFold(n_splits=4, batch_size = 32, epochs = 5
-#train only last layer
-#Classification Summary:
-#Average accuracy: 77.11%
-#Test Loss: 0.47622182965278625, Test Accuracy: 0.7777777910232544
-#Classification Summary:
-#Real images correctly classified: 116
-#Real images incorrectly classified: 23
-#Fake images correctly classified: 101
-#Fake images incorrectly classified: 39
-
-#KFold(n_splits=4, batch_size = 32, epochs = 5
-#train only last layer
-#Test Loss: 0.5492929220199585, Test Accuracy: 0.7992831468582153
-#Average accuracy: 88.79%
-#Classification Summary:
-#Real images correctly classified: 129
-#Real images incorrectly classified: 10
-#Fake images correctly classified: 94
-#Fake images incorrectly classified: 46
-#Classification Report:
-#              precision    recall  f1-score   support
-#
-#        Real       0.74      0.93      0.82       139
-#        Fake       0.90      0.67      0.77       140
-
-import random
-import numpy as np
-import os
-import pandas as pd
-import cv2
-import warnings
-from sklearn.model_selection import KFold
-import tensorflow as tf
-from sklearn.metrics import accuracy_score, confusion_matrix, ConfusionMatrixDisplay
-import matplotlib.pyplot as plt
-from sklearn.metrics import precision_score, recall_score, f1_score, classification_report
-
-# Ensure h5py is installed
-import h5py
-
-# Set the random seed for numpy, tensorflow, and python built-in random module
-np.random.seed(42)
-tf.random.set_seed(42)
-random.seed(42)
-
-warnings.filterwarnings("ignore", category=UserWarning, message=".*iCCP:.*")
-
-# Define data paths
-train_real_folder = 'datasets/training_set/real/'
-train_fake_folder = 'datasets/training_set/fake/'
-test_real_folder = 'datasets/test_set/real/'
-test_fake_folder = 'datasets/test_set/fake/'
-
-# Load train image paths and labels
-train_image_paths = []
-train_labels = []
-
-# Load train_real image paths and labels
-for filename in os.listdir(train_real_folder):
-    image_path = os.path.join(train_real_folder, filename)
-    label = 0  # Real images have label 0
-    train_image_paths.append(image_path)
-    train_labels.append(label)
-
-# Load train_fake image paths and labels
-for filename in os.listdir(train_fake_folder):
-    image_path = os.path.join(train_fake_folder, filename)
-    label = 1  # Fake images have label 1
-    train_image_paths.append(image_path)
-    train_labels.append(label)
-
-# Load test image paths and labels
-test_image_paths = []
-test_labels = []
-
-# Load test_real image paths and labels
-for filename in os.listdir(test_real_folder):
-    image_path = os.path.join(test_real_folder, filename)
-    label = 0  # Assuming test real images are all real (label 0)
-    test_image_paths.append(image_path)
-    test_labels.append(label)
-
-# Load test_fake image paths and labels
-for filename in os.listdir(test_fake_folder):
-    image_path = os.path.join(test_fake_folder, filename)
-    label = 1  # Assuming test fake images are all fake (label 1)
-    test_image_paths.append(image_path)
-    test_labels.append(label)
-
-# Create DataFrames
-train_dataset = pd.DataFrame({'image_path': train_image_paths, 'label': train_labels})
-test_dataset = pd.DataFrame({'image_path': test_image_paths, 'label': test_labels})
-
-# Function to preprocess images
-def preprocess_image(image_path):
-    """Loads, resizes, and normalizes an image."""
-    image = cv2.imread(image_path)
-    resized_image = cv2.resize(image, (224, 224))  # Target size defined here
-    normalized_image = resized_image.astype(np.float32) / 255.0
-    return normalized_image
-
-# Preprocess all images and convert labels to numpy arrays
-X = np.array([preprocess_image(path) for path in train_image_paths])
-Y = np.array(train_labels)
-
-# Define ResNet50 model
-resnet_model = tf.keras.applications.ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
-
-# Freeze all layers except the last one
-for layer in resnet_model.layers[:-1]:
-    layer.trainable = False
-
-# Modify final layer
-x = resnet_model.output
-x = tf.keras.layers.Flatten()(x)
-predictions = tf.keras.layers.Dense(1, activation='sigmoid')(x)  # Binary classification
-
-# Create new model with modified top
-new_model = tf.keras.models.Model(inputs=resnet_model.input, outputs=predictions)
-
-# Compile the new model
-new_model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
-
-# Set parameters for cross-validation
-kf = KFold(n_splits=4, shuffle=True, random_state=42)
-batch_size = 32
-epochs = 5
-weights_file = 'model_2.weights.h5'
-# Lists to store accuracy and loss for each fold
-accuracy_per_fold = []
-loss_per_fold = []
-
-# Perform K-Fold Cross-Validation
-for train_index, val_index in kf.split(X):
-    X_train, X_val = X[train_index], X[val_index]
-    Y_train, Y_val = Y[train_index], Y[val_index]
-    
-    # Load weights if they exist
-    if os.path.exists(weights_file):
-        new_model.load_weights(weights_file)
-        print(f"Loaded weights from {weights_file}")
-    
-    # Train only the last layer
-    history = new_model.fit(X_train, Y_train, epochs=epochs, batch_size=batch_size, verbose=1, validation_data=(X_val, Y_val))
-    
-    # Save weights after training
-    new_model.save_weights(weights_file)
-    print(f"Saved weights to {weights_file}")
-    
-    # Evaluate the model on the validation data
-    val_loss, val_accuracy = new_model.evaluate(X_val, Y_val)
-    
-    # Store the accuracy score for this fold
-    accuracy_per_fold.append(val_accuracy)
-    loss_per_fold.append(val_loss)
-    print(f'Fold accuracy: {val_accuracy*100:.2f}%')
-    print(f'Fold loss: {val_loss:.4f}')
-    
-# Print average accuracy and loss across all folds
-print(f'\nAverage accuracy across all folds: {np.mean(accuracy_per_fold)*100:.2f}%')
-print(f'Average loss across all folds: {np.mean(loss_per_fold):.4f}')
-
-# Evaluate the preprocessed test images using the final model
-test_loss, test_accuracy = new_model.evaluate(np.array([preprocess_image(path) for path in test_image_paths]), np.array(test_labels))
-print(f"\nTest Loss: {test_loss}, Test Accuracy: {test_accuracy}")
-
-# Predict labels for the test set
-predictions = new_model.predict(np.array([preprocess_image(path) for path in test_image_paths]))
-predicted_labels = (predictions > 0.5).astype(int).flatten()
-
-# Summarize the classification results
-true_real_correct = np.sum((np.array(test_labels) == 0) & (predicted_labels == 0))
-true_real_incorrect = np.sum((np.array(test_labels) == 0) & (predicted_labels == 1))
-true_fake_correct = np.sum((np.array(test_labels) == 1) & (predicted_labels == 1))
-true_fake_incorrect = np.sum((np.array(test_labels) == 1) & (predicted_labels == 0))
-
-print("\nClassification Summary:")
-print(f"Real images correctly classified: {true_real_correct}")
-print(f"Real images incorrectly classified: {true_real_incorrect}")
-print(f"Fake images correctly classified: {true_fake_correct}")
-print(f"Fake images incorrectly classified: {true_fake_incorrect}")
-
-# Print detailed classification report
-print("\nClassification Report:")
-print(classification_report(test_labels, predicted_labels, target_names=['Real', 'Fake']))
-
-# Plot confusion matrix
-cm = confusion_matrix(test_labels, predicted_labels)
-disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=['Real', 'Fake'])
-disp.plot(cmap=plt.cm.Blues)
-plt.title("Confusion Matrix")
-plt.show()
-
-# Plot training & validation accuracy values
-plt.figure(figsize=(12, 4))
-plt.subplot(1, 2, 1)
-plt.plot(history.history['accuracy'])
-plt.plot(history.history['val_accuracy'])
-plt.title('Model accuracy')
-plt.ylabel('Accuracy')
-plt.xlabel('Epoch')
-plt.legend(['Train', 'Validation'], loc='upper left')
-plt.xticks(np.arange(0, len(history.history['accuracy']), step=1), np.arange(1, len(history.history['accuracy']) + 1, step=1))
-
-# Plot training & validation loss values
-plt.subplot(1, 2, 2)
-plt.plot(history.history['loss'])
-plt.plot(history.history['val_loss'])
-plt.title('Model loss')
-plt.ylabel('Loss')
-plt.xlabel('Epoch')
-plt.legend(['Train', 'Validation'], loc='upper left')
-plt.xticks(np.arange(0, len(history.history['loss']), step=1), np.arange(1, len(history.history['loss']) + 1, step=1))
-
-plt.tight_layout()
-plt.show()
-
-# Plot validation accuracy and loss per fold
-plt.figure(figsize=(12, 4))
-plt.subplot(1, 2, 1)
-plt.plot(range(1, kf.get_n_splits() + 1), accuracy_per_fold, marker='o')
-plt.title('Validation Accuracy per Fold')
-plt.xlabel('Fold')
-plt.ylabel('Accuracy')
-
-plt.subplot(1, 2, 2)
-plt.plot(range(1, kf.get_n_splits() + 1), loss_per_fold, marker='o')
-plt.title('Validation Loss per Fold')
-plt.xlabel('Fold')
-plt.ylabel('Loss')
-
-plt.tight_layout()
-plt.show()
+
+import random
+import numpy as np
+import os
+import pandas as pd
+import cv2
+import warnings
+from sklearn.model_selection import KFold
+import tensorflow as tf
+from sklearn.metrics import accuracy_score, confusion_matrix, ConfusionMatrixDisplay
+import matplotlib.pyplot as plt
+from sklearn.metrics import precision_score, recall_score, f1_score, classification_report
+
+# Ensure h5py is installed
+import h5py
+
+# Set the random seed for numpy, tensorflow, and python built-in random module
+np.random.seed(42)
+tf.random.set_seed(42)
+random.seed(42)
+
+warnings.filterwarnings("ignore", category=UserWarning, message=".*iCCP:.*")
+
+# Define data paths
+train_real_folder = 'datasets/training_set/real/'
+train_fake_folder = 'datasets/training_set/fake/'
+test_real_folder = 'datasets/test_set/real/'
+test_fake_folder = 'datasets/test_set/fake/'
+
+# Load train image paths and labels
+train_image_paths = []
+train_labels = []
+
+# Load train_real image paths and labels
+for filename in os.listdir(train_real_folder):
+    image_path = os.path.join(train_real_folder, filename)
+    label = 0  # Real images have label 0
+    train_image_paths.append(image_path)
+    train_labels.append(label)
+
+# Load train_fake image paths and labels
+for filename in os.listdir(train_fake_folder):
+    image_path = os.path.join(train_fake_folder, filename)
+    label = 1  # Fake images have label 1
+    train_image_paths.append(image_path)
+    train_labels.append(label)
+
+# Load test image paths and labels
+test_image_paths = []
+test_labels = []
+
+# Load test_real image paths and labels
+for filename in os.listdir(test_real_folder):
+    image_path = os.path.join(test_real_folder, filename)
+    label = 0  # Assuming test real images are all real (label 0)
+    test_image_paths.append(image_path)
+    test_labels.append(label)
+
+# Load test_fake image paths and labels
+for filename in os.listdir(test_fake_folder):
+    image_path = os.path.join(test_fake_folder, filename)
+    label = 1  # Assuming test fake images are all fake (label 1)
+    test_image_paths.append(image_path)
+    test_labels.append(label)
+
+# Create DataFrames
+train_dataset = pd.DataFrame({'image_path': train_image_paths, 'label': train_labels})
+test_dataset = pd.DataFrame({'image_path': test_image_paths, 'label': test_labels})
+
+# Function to preprocess images
+def preprocess_image(image_path):
+    """Loads, resizes, and normalizes an image."""
+    image = cv2.imread(image_path)
+    resized_image = cv2.resize(image, (224, 224))  # Target size defined here
+    normalized_image = resized_image.astype(np.float32) / 255.0
+    return normalized_image
+
+# Preprocess all images and convert labels to numpy arrays
+X = np.array([preprocess_image(path) for path in train_image_paths])
+Y = np.array(train_labels)
+
+# Define ResNet50 model
+resnet_model = tf.keras.applications.ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
+
+# Freeze all layers except the last one
+for layer in resnet_model.layers[:-1]:
+    layer.trainable = False
+
+# Modify final layer
+x = resnet_model.output
+x = tf.keras.layers.Flatten()(x)
+predictions = tf.keras.layers.Dense(1, activation='sigmoid')(x)  # Binary classification
+
+# Create new model with modified top
+new_model = tf.keras.models.Model(inputs=resnet_model.input, outputs=predictions)
+
+# Compile the new model
+new_model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
+
+# Set parameters for cross-validation
+kf = KFold(n_splits=4, shuffle=True, random_state=42)
+batch_size = 32
+epochs = 5
+weights_file = 'model_2.weights.h5'
+# Lists to store accuracy and loss for each fold
+accuracy_per_fold = []
+loss_per_fold = []
+
+# Perform K-Fold Cross-Validation
+for train_index, val_index in kf.split(X):
+    X_train, X_val = X[train_index], X[val_index]
+    Y_train, Y_val = Y[train_index], Y[val_index]
+    
+    # Load weights if they exist
+    if os.path.exists(weights_file):
+        new_model.load_weights(weights_file)
+        print(f"Loaded weights from {weights_file}")
+    
+    # Train only the last layer
+    history = new_model.fit(X_train, Y_train, epochs=epochs, batch_size=batch_size, verbose=1, validation_data=(X_val, Y_val))
+    
+    # Save weights after training
+    new_model.save_weights(weights_file)
+    print(f"Saved weights to {weights_file}")
+    
+    # Evaluate the model on the validation data
+    val_loss, val_accuracy = new_model.evaluate(X_val, Y_val)
+    
+    # Store the accuracy score for this fold
+    accuracy_per_fold.append(val_accuracy)
+    loss_per_fold.append(val_loss)
+    print(f'Fold accuracy: {val_accuracy*100:.2f}%')
+    print(f'Fold loss: {val_loss:.4f}')
+    
+# Print average accuracy and loss across all folds
+print(f'\nAverage accuracy across all folds: {np.mean(accuracy_per_fold)*100:.2f}%')
+print(f'Average loss across all folds: {np.mean(loss_per_fold):.4f}')
+
+# Evaluate the preprocessed test images using the final model
+test_loss, test_accuracy = new_model.evaluate(np.array([preprocess_image(path) for path in test_image_paths]), np.array(test_labels))
+print(f"\nTest Loss: {test_loss}, Test Accuracy: {test_accuracy}")
+
+# Predict labels for the test set
+predictions = new_model.predict(np.array([preprocess_image(path) for path in test_image_paths]))
+predicted_labels = (predictions > 0.5).astype(int).flatten()
+
+# Summarize the classification results
+true_real_correct = np.sum((np.array(test_labels) == 0) & (predicted_labels == 0))
+true_real_incorrect = np.sum((np.array(test_labels) == 0) & (predicted_labels == 1))
+true_fake_correct = np.sum((np.array(test_labels) == 1) & (predicted_labels == 1))
+true_fake_incorrect = np.sum((np.array(test_labels) == 1) & (predicted_labels == 0))
+
+print("\nClassification Summary:")
+print(f"Real images correctly classified: {true_real_correct}")
+print(f"Real images incorrectly classified: {true_real_incorrect}")
+print(f"Fake images correctly classified: {true_fake_correct}")
+print(f"Fake images incorrectly classified: {true_fake_incorrect}")
+
+# Print detailed classification report
+print("\nClassification Report:")
+print(classification_report(test_labels, predicted_labels, target_names=['Real', 'Fake']))
+
+# Plot confusion matrix
+cm = confusion_matrix(test_labels, predicted_labels)
+disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=['Real', 'Fake'])
+disp.plot(cmap=plt.cm.Blues)
+plt.title("Confusion Matrix")
+plt.show()
+
+# Plot training & validation accuracy values
+plt.figure(figsize=(12, 4))
+plt.subplot(1, 2, 1)
+plt.plot(history.history['accuracy'])
+plt.plot(history.history['val_accuracy'])
+plt.title('Model accuracy')
+plt.ylabel('Accuracy')
+plt.xlabel('Epoch')
+plt.legend(['Train', 'Validation'], loc='upper left')
+plt.xticks(np.arange(0, len(history.history['accuracy']), step=1), np.arange(1, len(history.history['accuracy']) + 1, step=1))
+
+# Plot training & validation loss values
+plt.subplot(1, 2, 2)
+plt.plot(history.history['loss'])
+plt.plot(history.history['val_loss'])
+plt.title('Model loss')
+plt.ylabel('Loss')
+plt.xlabel('Epoch')
+plt.legend(['Train', 'Validation'], loc='upper left')
+plt.xticks(np.arange(0, len(history.history['loss']), step=1), np.arange(1, len(history.history['loss']) + 1, step=1))
+
+plt.tight_layout()
+plt.show()
+
+# Plot validation accuracy and loss per fold
+plt.figure(figsize=(12, 4))
+plt.subplot(1, 2, 1)
+plt.plot(range(1, kf.get_n_splits() + 1), accuracy_per_fold, marker='o')
+plt.title('Validation Accuracy per Fold')
+plt.xlabel('Fold')
+plt.ylabel('Accuracy')
+
+plt.subplot(1, 2, 2)
+plt.plot(range(1, kf.get_n_splits() + 1), loss_per_fold, marker='o')
+plt.title('Validation Loss per Fold')
+plt.xlabel('Fold')
+plt.ylabel('Loss')
+
+plt.tight_layout()
+plt.show()