Convolutional Neural Networks (CNNs) in Keras

Convolutional Neural Networks (CNNs) are a class of deep neural networks that are particularly effective for image recognition and processing. Keras, a high-level neural networks API, makes it easy to build and train CNNs. In this tutorial, we will explore how to use Keras to create a CNN for image classification.

Prerequisites

Before you start, make sure you have the following prerequisites installed:

Python 3.5+
Keras
TensorFlow or Theano

You can install Keras using pip:

pip install keras

Building the CNN

To build a CNN in Keras, we will use the Sequential API, which allows us to stack layers one after another.

from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

model = Sequential()

# Add a convolutional layer with 32 filters and a kernel size of 3x3
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(64, 64, 3)))

# Add a max pooling layer with a pool size of 2x2
model.add(MaxPooling2D(pool_size=(2, 2)))

# Flatten the output of the previous layer
model.add(Flatten())

# Add a fully connected layer with 128 units and a ReLU activation function
model.add(Dense(128, activation='relu'))

# Add the output layer with softmax activation function
model.add(Dense(10, activation='softmax'))

Compiling and Training the Model

After building the model, we need to compile it with an optimizer, loss function, and metrics.

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

Next, we can train the model using our dataset.

# Assuming you have your training data in X_train and y_train variables
model.fit(X_train, y_train, epochs=10, batch_size=32)

Visualizing the Model

Keras provides a way to visualize the architecture of the model using the plot_model function.

from keras.utils.vis_utils import plot_model

plot_model(model, to_file='model.png', show_shapes=True)

This will generate a file named model.png in the current directory, showing the architecture of the model.

Conclusion