Single and Multi layer

 # -*- coding: utf-8 -*-

"""Single and Multi Layer Perceptron.ipynb

Automatically generated by Colaboratory.

Original file is located at

    https://colab.research.google.com/drive/1sUwF-aPoUh-5eiqZRHDTrFQqz01k8xZs

"""

# importing modules

import tensorflow as tf

import numpy as np

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Flatten

from tensorflow.keras.layers import Dense

from tensorflow.keras.layers import Activation

import matplotlib.pyplot as plt

import plotly.express as px

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

# Cast the records into float values

x_train = x_train.astype('float32')

x_test = x_test.astype('float32')

# normalize image pixel values by dividing

# by 255

gray_scale = 255

x_train /= gray_scale

x_test /= gray_scale

print("Feature matrix:", x_train.shape)

print("Target matrix:", x_test.shape)

print("Feature matrix:", y_train.shape)

print("Target matrix:", y_test.shape)

fig, ax = plt.subplots(10, 10)

k = 0

for i in range(10):

    for j in range(10):

        ax[i][j].imshow(x_train[k].reshape(28, 28),

                        aspect='auto')

        k += 1

plt.show()

single_layer_model= Sequential([

   

    # reshape 28 row * 28 column data to 28*28 rows

    Flatten(input_shape=(28, 28)),

   

    # dense layer 1

    Dense(256, activation='sigmoid'),

   

])

multi_layer_model= Sequential([

   

    # reshape 28 row * 28 column data to 28*28 rows

    Flatten(input_shape=(28, 28)),

   

    # dense layer 1

    Dense(256, activation='sigmoid'),

   

    # dense layer 2

  Dense(128, activation='sigmoid'),

   

    # output layer

    Dense(10, activation='sigmoid'),

])

single_layer_model.compile(optimizer='adam',

            loss='sparse_categorical_crossentropy',

            metrics=['accuracy'])

multi_layer_model.compile(optimizer='adam',

            loss='sparse_categorical_crossentropy',

            metrics=['accuracy'])

singleresults = single_layer_model.evaluate(x_test, y_test, verbose = 0)

multiresults = multi_layer_model.evaluate(x_test, y_test, verbose = 0)

#print('test loss, test acc:', results)

print("Single layer Accuracy:",singleresults[1]*100)

print("Multi layer Accuracy:",multiresults[1]*100)

sm= [singleresults[1],multiresults[1]]

plt.bar(['Single Layer', 'Multi Layer'],sm, width=0.4 ,color=['r','y'])

plt.plot(singleresults[1],linestyle = 'dashed')

plt.show()