[1]. Tool: Claude
      Prompt: How can I efficiently import a large amount of JPEG images into python for use with tensorflow while normalizing and randomizing the dataset?
      Output:
            from tensorflow.keras.preprocessing import image_dataset_from_directory

            # Load color JPEG images from directory structure:
            # Data/
            #   ├── damage/
            #   └── no_damage/

            dataset = image_dataset_from_directory(
            'Data',
            image_size=(224, 224),
            batch_size=32,
            label_mode='binary',
            color_mode='rgb',  # Explicitly load as color (this is the default)
            shuffle=True,
            seed=42
            )

            # Normalize pixel values to [0, 1] range for better training
            normalization_layer = tf.keras.layers.Rescaling(1./255)
            dataset = dataset.map(lambda x, y: (normalization_layer(x), y))

            # Optimize performance
            dataset = dataset.prefetch(tf.data.AUTOTUNE)

            print(f"Dataset created. Each batch shape: (batch_size, 224, 224, 3)")

[2]. Tool: Google AI Mode
      Prompt: How can I ensure my GPU memory is emptied between model training sessions?
      Output: import tensorflow as tf
            import gc

            # Load and use your model
            # ...

            del model  # Delete the model object
            tf.keras.backend.clear_session()  # Clear the Keras backend session
            gc.collect()  # Force garbage collection

[2]. Tool: Google AI Mode
      Prompt: vgg16 with binary classification
      Output: import tensorflow as tf
            from tensorflow.keras.applications import VGG16
            from tensorflow.keras.models import Sequential, Model
            from tensorflow.keras.layers import Dense, Flatten, Dropout
            from tensorflow.keras.optimizers import Adam
            from tensorflow.keras.losses import binary_crossentropy

            # 1. Load VGG16 without the top layer
            IMG_SIZE = (224, 224) # VGG16 default input size
            vgg_base = VGG16(weights='imagenet', include_top=False, input_shape=IMG_SIZE + (3,))

            # 2. Freeze the convolutional base
            vgg_base.trainable = False

            # 3. Create a new model with custom top layers
            model = Sequential()
            model.add(vgg_base)
            model.add(Flatten())
            model.add(Dense(256, activation='relu'))
            model.add(Dropout(0.5)) # Regularization to prevent overfitting
            model.add(Dense(1, activation='sigmoid')) # Single neuron with sigmoid for binary classification

            # 4. Compile the model
            model.compile(
            optimizer=Adam(learning_rate=0.0001), # Lower learning rate often better for transfer learning
            loss=binary_crossentropy,
            metrics=['accuracy']
            )

            # 5. Train the model (using ImageDataGenerator for data preparation)
            # ... data loading and augmentation code here ...
            # model.fit(...)