10/14/24, 11:30 AM A3 - Jupyter Notebook

In [2]: Name: Jay Uddhav Shinde

Roll No : 70
BE IT

In [ ]: #Build the Image classification model by dividing the model into following 4 stages:
#1.Loading and preprocessing the image data
#2.Defining the model's architecture
#3.Training the model
#4.Estimating the model's performance

In [22]: import numpy as np

import pandas as pd
import random
import tensorflow as tf
import matplotlib.pyplot as plt
from sklearn.metrics import accuracy_score
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Flatten, Conv2D,Dense,MaxPooling2D
from tensorflow.keras.optimizers import SGD
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.datasets import mnist

In [23]: # Loading and preprocessing the image data

(X_train, y_train),(X_test, y_test) = mnist.load_data()

In [24]: print(X_train.shape)

(60000, 28, 28)

In [25]: X_train[0].min(),X_train[0].max()

Out[25]: (0, 255)

In [26]: X_train = (X_train - 0.0) / (255.0 - 0.0)

X_test = (X_test - 0.0) / (255.0 - 0.0)
X_train[0].min(), X_train[0].max() (0.0,
1.0)
(0.0, 1.0)
Out[26]:

localhost:8888/notebooks/A3.ipynb 1/5
10/14/24, 11:30 AM A3 - Jupyter Notebook

In [27]: def plot_digit(image, digit, plt, i):

plt.subplot(4, 5, i + 1) plt.imshow(image,
cmap=plt.get_cmap('gray'))
plt.title(f"Digit: {digit}") plt.xticks([])
plt.yticks([])

plt.figure(figsize=(16, 10))
for i in range(20):
plot_digit(X_train[i], y_train[i], plt, i)
plt.show()

In [28]: X_tarin = X_train.reshape((X_train.shape+ (1,)))

X_test = X_test.reshape((X_test.shape+(1,)))

In [29]: y_train[0:20]

Out[29]: array([5, 0, 4, 1, 9, 2, 1, 3, 1, 4, 3, 5, 3, 6, 1, 7, 2, 8, 6, 9],

dtype=uint8)

In [30]: # Defining the model's architecture

model = Sequential([
Conv2D(32,(3,3), activation="relu",input_shape=(28,28,1)),
MaxPooling2D((2,2)),
Flatten(),
Dense(100,activation="relu"),
Dense(10,activation="softmax")
])

In [31]: optimizer = SGD(learning_rate=0.01, momentum=0.9)

model.compile(
optimizer=optimizer,
loss="sparse_categorical_crossentropy",
metrics=["accuracy"]
)

localhost:8888/notebooks/A3.ipynb 2/5
10/14/24, 11:30 AM A3 - Jupyter Notebook

In [32]: model.summary()

Model: "sequential_2"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_3 (Conv2D) (None, 26, 26, 32) 320

max_pooling2d_3 (MaxPoolin (None, 13, 13, 32) 0

g2D)
flatten_2 (Flatten)
(None, 5408) 0

dense_4 (Dense) (None, 100) 540900

dense_5 (Dense) (None, 10) 1010

=================================================================
Total params: 542230 (2.07 MB)
Trainable params: 542230 (2.07 MB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

In [33]: #Training and testing the model

Model_log=model.fit(X_train, y_train, epochs=10, batch_size=15,verbose=1,validation_data=0);

Epoch 1/10
4000/4000 [==============================] - 52s 13ms/step - loss: 0.1749 - accuracy: 0.9453
Epoch 2/10
4000/4000 [==============================] - 50s 12ms/step - loss: 0.0560 - accuracy: 0.9829
Epoch 3/10
4000/4000 [==============================] - 50s 13ms/step - loss: 0.0346 - accuracy: 0.9890
Epoch 4/10
4000/4000 [==============================] - 50s 12ms/step - loss: 0.0241 - accuracy: 0.9924
Epoch 5/10
4000/4000 [==============================] - 50s 12ms/step - loss: 0.0153 - accuracy: 0.9953
Epoch 6/10
4000/4000 [==============================] - 50s 13ms/step - loss: 0.0107 - accuracy: 0.9968
Epoch 7/10
4000/4000 [==============================] - 50s 13ms/step - loss: 0.0070 - accuracy: 0.9977
Epoch 8/10
4000/4000 [==============================] - 50s 12ms/step - loss: 0.0050 - accuracy: 0.9985
Epoch 9/10
4000/4000 [==============================] - 50s 13ms/step - loss: 0.0023 - accuracy: 0.9995
Epoch 10/10
4000/4000 [==============================] - 50s 12ms/step - loss: 0.0022 - accuracy: 0.9994

localhost:8888/notebooks/A3.ipynb 3/5
10/14/24, 11:30 AM A3 - Jupyter Notebook

In [34]: plt.figure(figsize=(16, 10))

for i in range(20):
image = random.choice(X_test).squeeze()
digit = np.argmax(model.predict(image.reshape((1, 28, 28, 1)))[0], axis=-1)
plot_digit(image, digit, plt, i)
plt.show()

1/1 [==============================] - 0s 249ms/step

1/1 [==============================] - 0s 48ms/step
1/1 [==============================] - 0s 47ms/step
1/1 [==============================] - 0s 55ms/step
1/1 [==============================] - 0s 51ms/step
1/1 [==============================] - 0s 47ms/step
1/1 [==============================] - 0s 39ms/step
1/1 [==============================] - 0s 47ms/step
1/1 [==============================] - 0s 47ms/step
1/1 [==============================] - 0s 63ms/step
1/1 [==============================] - 0s 43ms/step
1/1 [==============================] - 0s 48ms/step
1/1 [==============================] - 0s 47ms/step
1/1 [==============================] - 0s 49ms/step
1/1 [==============================] - 0s 47ms/step
1/1 [==============================] - 0s 39ms/step
1/1 [==============================] - 0s 49ms/step
1/1 [==============================] - 0s 52ms/step
1/1 [==============================] - 0s 48ms/step
1/1 [==============================] - 0s 47ms/step

In [35]: predictions = np.argmax(model.predict(X_test),axis=-1)

accuracy_score(y_test,predictions)

313/313 [==============================] - 2s 7ms/step

Out[35]: 0.9879

localhost:8888/notebooks/A3.ipynb 4/5
10/14/24, 11:30 AM A3 - Jupyter Notebook

In [36]: n = random.randint(0,9999)
plt.imshow(X_test[n])
plt.show()

In [38]: predicted_value = model.predict(X_test)

print("Handwritten number in the image is = %d" %np.argmax(predicted_value[n]))

313/313 [==============================] - 2s 7ms/step

Handwritten number in the image is = 5

In [39]: # Estimating the model's performance

score = model.evaluate(X_test,y_test,verbose=0)
print('Test loss:' , score[0])
print('Testaccuracy:',score[1])

Test loss: 0.044867195188999176

Testaccuracy: 0.9879000186920166

In [ ]:

localhost:8888/notebooks/A3.ipynb 5/5