Flattening

Pooling

Flattening is nothing but converting a 3D or 2D matrix into a 1D input for the model this will be our last step to process the image and connect the inputs to a fully connected dense layer for further classification.

To sum up, The way a convolution neural network works is:

Applying convolution to find different importand features inside the image

syntax: model.add(layers.Conv2D(no. of kernels, size of the kernel, activation=’relu’, input_shape)

Applying pooling to compress the image without losing its features

syntax: model.add(layers.MaxPooling2D((size of the kernel)))

FLattening it to a 1-dimensional input from a 3D[color images] or 2D [Black and white images] to pass into the model

syntax: model.add(layers.Flatten()

Fully connected input and hidden layers to play with weights and biases and activation functions and optimizers.
Wola! You have built the best image classifier.

A typical CNN model will look like:

Python

# Importing the library
import tensorflow as tf
from tensorflow import keras
 
# Designing the model
model = tf.keras.models.Sequential([
    # Convolutional layer1
    tf.keras.layers.Conv2D(
        32, (3, 3), activation='relu', input_shape=(32, 32, 3))
    tf.keras.layers.MaxPooling2D((2, 2))  # Pooling
    # COnvolutional layer2
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu')
    tf.keras.layers.MaxPooling2D((2, 2))  # Pooling
    # COnvolutional layer3
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu')
    tf.keras.layers.MaxPooling2D((2, 2))  # Pooling
    # Flattening the input
    tf.keras.layers.Flatten(),
    # Fully connected layers
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(256, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])
 
# Compiling the model
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(
                  from_logits=True),
              metrics=['accuracy'])
 
# FItting the data to a model
history = model.fit(train_images, train_labels, epochs=10,
                    validation_data=(test_images, test_labels))

Output:

Working of Convolutional Neural Network (CNN) in Tensorflow

In this article, we are going to see the working of convolution neural networks with TensorFlow a powerful machine learning library to create neural networks.

Now to know, how a convolution neural network lets break it into parts. the 3 most important parts of this convolution neural networks are,

Convolution
Pooling
Flattening

These 3 actions are the very special things that make convolution neural networks perform way better compared with other artificial neural networks. Now, let’s discuss them in detail,

Tags:

#Neural Network #Tensorflow #AI-ML-DS #Deep Learning

Pooling

Flattening

A typical CNN model will look like:

Python

Working of Convolutional Neural Network (CNN) in Tensorflow

Similar Reads

Contact Us