VGGNet Keras Implementation

README.md

 VGGNet Keras Implementation

This script contains an implementation of the VGGNet architecture using Keras. The module provides functions to create VGG16 and VGG19 models, as well as utility functions to process images for use with the models.

Dependencies

• Python 3.6+
• OpenCV
• Keras
• NumPy
• Usage

vggnet_keras_implementation.py

"""
VGGNet Keras Implementation

This module provides an implementation of the VGGNet architecture using Keras.
It contains functions to create VGG16 and VGG19 models, as well as utility
functions to preprocess images for use with the models.
"""

from keras.optimizers import SGD
from keras.models import Sequential
import cv2 as opencv
import numpy as np
from keras.layers import Dense, Dropout, Flatten, MaxPooling2D, ZeroPadding2D,\
    Convolution2D


def vgg16():
    """
    Creates a VGG16 model using Keras.

    Returns:
        model (Sequential): The VGG16 model.
    """

    model = Sequential()

    # Define the VGG16 architecture.
    # Add layers, each block represents a group of layers in the VGG16 model

    # 224 x 224 x 3
    model = Sequential()
    model.add(ZeroPadding2D((1, 1), input_shape=(224, 224, 3)))
    model.add(Convolution2D(64, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(64, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))

    # 224 x 225 x 64
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(128, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(128, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))

    # 112 x 112 x 128
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(256, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(256, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(256, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(256, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))

    # 56 x 56 x 256
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))

    # 28 x 28 x 512 --- # 14 x 14 x 512 --- # 1 x 1 x 1000
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(ZeroPadding2D((1, 1)))
    model.add(Convolution2D(512, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))

    # 1 x 1 x 4096 --- # 1 x 1 x 1000
    model.add(Flatten())
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(1000, activation='softmax'))

    # Load Weights
    model.load_weights('./vgg16_weights.h5')

    return model


def vgg19():
    """
    Placeholder function for VGG19.
    """
    return False


def preprocess_image(image_path):
    """
    Preprocess an image for use with VGGNet models.

    Args:
        image_path (str): Path to the input image file.

    Returns:
        im (numpy.ndarray): Preprocessed image.
    """

    image = opencv.imread(image_path)
    im = opencv.resize(image, (224, 224)).astype(np.float32)

    # Subtract mean RGB values for VGGNet
    im[:, :, 0] -= 103.939
    im[:, :, 1] -= 116.779
    im[:, :, 2] -= 123.68
    im = im.transpose((2, 0, 1))
    im = np.expand_dims(im, axis=0)

    return im


def main():
    """
    Main function to run the VGGNet model on an input image.
    """

    image_path = 'cat.jpg'

    # Preprocess the input image
    im = preprocess_image(image_path)

    # Load the model
    model = vgg16()

    # Compile the model
    sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
    model.compile(optimizer=sgd, loss='categorical_crossentropy')

    # Predict using the model
    out = model.predict(im)
    print(np.argmax(out))


if __name__ == '__main__':
    main()