Deep Dive To Convolution Neural Network

LeNet is a convolutional neural network structure proposed by Yann Lecun in 1998. It was the first big breakthrough in the world of deep learning and computer vision. In general, LeNet refers to LeNet-5.This architecture was the first time applied over the MNIST dataset to recognize the handwritten character.

Architecture

Input Layer -The size of the input image is uniformly normalized to 32 * 32.

Convolutions - Convolution is the process of adding each element of the image to its local neighbors, weighted by the kernel. This is related to a form of mathematical convolution. The matrix operation being performed—convolution—is not traditional matrix multiplication, despite being similarly denoted by *

Subsampling - It means pooling ,its function is to progressively reduce the spatial size of the representation to reduce the number of parameters and computation in the network.

Architecture Consist Of Following Layers

• C1 layer-convolutional layer
• S2 layer-pooling layer
• C3 layer-convolutional layer
• S4 layer-pooling layer
• C5 layer-convolution layer
• F6 layer-fully connected layer or output layer - The output layer is also a fully connected layer, with a total of 10 nodes, which respectively represent the numbers 0 to 9, and if the value of node i is 0, the result of network recognition is the number

Sample Code

import tensorflow as tf
from tensorflow import keras
from keras.layers import Conv2D,MaxPool2D,Flatten,Dense
from keras.datasets import mnist

# Data preprocessing
(x_train,y_train),(x_test,y_test)=mnist.load_data()
x_train=x_train.reshape(x_train.shape[0],28,28,1)
x_test=x_test.reshape(x_test.shape[0],28,28,1)
x_train=x_train/225
x_test=x_test/225
y_train=keras.utils.to_categorical(y_train,10)
y_test=keras.utils.to_categorical(y_test,10)
 
# model 
model = keras.Sequential()

model.add(layers.Conv2D(filters=6, kernel_size=(3, 3), activation='relu', input_shape=(32,32,1)))
model.add(layers.AveragePooling2D())

model.add(layers.Conv2D(filters=16, kernel_size=(3, 3), activation='relu'))
model.add(layers.AveragePooling2D())

model.add(layers.Flatten())

model.add(layers.Dense(units=120, activation='relu'))

model.add(layers.Dense(units=84, activation='relu'))

model.add(layers.Dense(units=10, activation = 'softmax'))
# model compile
model.compile(optimizer="adam",loss='categorical_crossentropy',metrics=['accuracy'])
# model fitting
model.fit(x_train,y_train,batch_size=128,epochs=10,validation_data=(x_test,y_test),verbose=1)

score=classifier.evaluate(x_test,y_test)
print('Test loss:',score[0])
print('Test acuuracy:',score[1])
# prediction
pred=classifier.predict(x_test[index].reshape(1,28,28,1))
print(pred.argmax())