15/04/2025, 08:38 DL3

PIYUSH AHIRE 39

In [1]: from __future__ import absolute_import, division, print_function

# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow import keras
# Helper libraries
import numpy as np
import matplotlib.pyplot as plt

In [2]: fashion_mnist = keras.datasets.fashion_mnist

(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_da

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-dataset

s/train-labels-idx1-ubyte.gz
29515/29515 ━━━━━━━━━━━━━━━━━━━━ 0s 2us/step
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-dataset
s/train-images-idx3-ubyte.gz
26421880/26421880 ━━━━━━━━━━━━━━━━━━━━ 21s 1us/step
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-dataset
s/t10k-labels-idx1-ubyte.gz
5148/5148 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-dataset
s/t10k-images-idx3-ubyte.gz
4422102/4422102 ━━━━━━━━━━━━━━━━━━━━ 6s 1us/step

In [3]: class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',

'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

In [4]: train_images.shape

Out[4]: (60000, 28, 28)

In [5]: len(train_labels)

Out[5]: 60000

In [6]: train_labels

Out[6]: array([9, 0, 0, ..., 3, 0, 5], dtype=uint8)

In [7]: test_images.shape

Out[7]: (10000, 28, 28)

In [8]: len(test_labels)

Out[8]: 10000

In [9]: plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid(False)
plt.show()

file:///C:/Users/deshm/Downloads/DL3 (2).html 1/7

15/04/2025, 08:38 DL3

In [10]: train_images = train_images / 255.0

test_images = test_images / 255.0

In [11]: plt.figure(figsize=(10,10))
for i in range(25):
plt.subplot(5,5,i+1)
plt.xticks([])
plt.yticks([])
plt.grid(False)
plt.imshow(train_images[i], cmap=plt.cm.binary)
plt.xlabel(class_names[train_labels[i]])
plt.show()

file:///C:/Users/deshm/Downloads/DL3 (2).html 2/7

15/04/2025, 08:38 DL3

In [12]: model = keras.Sequential([

keras.layers.Flatten(input_shape=(28, 28)),
keras.layers.Dense(128, activation=tf.nn.relu),
keras.layers.Dense(10, activation=tf.nn.softmax)
])

C:\Users\deshm\anaconda3\Lib\site-packages\keras\src\layers\reshaping\flatten.py:
37: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. Wh
en using Sequential models, prefer using an `Input(shape)` object as the first la
yer in the model instead.
super().__init__(**kwargs)

In [13]: model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])

In [14]: model.fit(train_images, train_labels, epochs=5)

file:///C:/Users/deshm/Downloads/DL3 (2).html 3/7

15/04/2025, 08:38 DL3

Epoch 1/5
1875/1875 ━━━━━━━━━━━━━━━━━━━━ 7s 3ms/step - accuracy: 0.7868 - loss: 0.6169
Epoch 2/5
1875/1875 ━━━━━━━━━━━━━━━━━━━━ 5s 3ms/step - accuracy: 0.8635 - loss: 0.3778
Epoch 3/5
1875/1875 ━━━━━━━━━━━━━━━━━━━━ 6s 3ms/step - accuracy: 0.8757 - loss: 0.3431
Epoch 4/5
1875/1875 ━━━━━━━━━━━━━━━━━━━━ 5s 3ms/step - accuracy: 0.8850 - loss: 0.3124
Epoch 5/5
1875/1875 ━━━━━━━━━━━━━━━━━━━━ 5s 3ms/step - accuracy: 0.8897 - loss: 0.2928
Out[14]: <keras.src.callbacks.history.History at 0x189591adfd0>

In [15]: test_loss, test_acc = model.evaluate(test_images, test_labels)

print('Test accuracy:', test_acc)

313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8773 - loss: 0.3388

Test accuracy: 0.8783000111579895

In [16]: predictions = model.predict(test_images)

313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step

In [17]: predictions[0]

Out[17]: array([8.9694855e-05, 3.8969080e-07, 7.9476223e-07, 2.6765531e-06,

2.6583541e-06, 3.6756277e-02, 4.5844458e-06, 5.0728031e-02,
2.0136039e-03, 9.1040134e-01], dtype=float32)

In [18]: np.argmax(predictions[0])

Out[18]: 9

In [19]: test_labels[0]

Out[19]: 9

In [20]: import numpy as np

import matplotlib.pyplot as plt

def plot_image(i, predictions_array, true_label, img):

predictions_array, true_label, img = predictions_array[i], true_label[i], im
plt.grid(False)
plt.xticks([])
plt.yticks([])
plt.imshow(img, cmap=plt.cm.binary)

predicted_label = np.argmax(predictions_array)
if predicted_label == true_label:
color = 'blue'
else:
color = 'red'

plt.xlabel(
"{} {:2.0f}% ({})".format(
class_names[predicted_label],
100 * np.max(predictions_array),
class_names[true_label]
),
color=color
)

file:///C:/Users/deshm/Downloads/DL3 (2).html 4/7

15/04/2025, 08:38 DL3

def plot_value_array(i, predictions_array, true_label):

predictions_array, true_label = predictions_array[i], true_label[i]
plt.grid(False)
plt.xticks([])
plt.yticks([])
thisplot = plt.bar(range(10), predictions_array, color="#777777")
plt.ylim([0, 1])
predicted_label = np.argmax(predictions_array)
thisplot[predicted_label].set_color('red')
thisplot[true_label].set_color('blue')

In [21]: i = 0
plt.figure(figsize=(6,3))
plt.subplot(1,2,1)
plot_image(i, predictions, test_labels, test_images)
plt.subplot(1,2,2)
plot_value_array(i, predictions, test_labels)
plt.show()

In [22]: i = 12
plt.figure(figsize=(6,3))
plt.subplot(1,2,1)
plot_image(i, predictions, test_labels, test_images)
plt.subplot(1,2,2)
plot_value_array(i, predictions, test_labels)
plt.show()

file:///C:/Users/deshm/Downloads/DL3 (2).html 5/7

15/04/2025, 08:38 DL3

In [23]: # Plot the first X test images, their predicted label, and the true label
# Color correct predictions in blue, incorrect predictions in red
num_rows = 5
num_cols = 3
num_images = num_rows*num_cols
plt.figure(figsize=(2*2*num_cols, 2*num_rows))
for i in range(num_images):
plt.subplot(num_rows, 2*num_cols, 2*i+1)
plot_image(i, predictions, test_labels, test_images)
plt.subplot(num_rows, 2*num_cols, 2*i+2)
plot_value_array(i, predictions, test_labels)
plt.show()

In [24]: # Grab an image from the test dataset

img = test_images[0]
print(img.shape)

(28, 28)

In [25]: # Add the image to a batch where it's the only member.
img = (np.expand_dims(img,0))
print(img.shape)

(1, 28, 28)

In [26]: predictions_single = model.predict(img)

print(predictions_single)

file:///C:/Users/deshm/Downloads/DL3 (2).html 6/7

15/04/2025, 08:38 DL3

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 26ms/step

[[8.9694840e-05 3.8969074e-07 7.9476291e-07 2.6765551e-06 2.6583566e-06
3.6756210e-02 4.5844454e-06 5.0728064e-02 2.0136037e-03 9.1040123e-01]]

In [27]: plot_value_array(0, predictions_single, test_labels)

_ = plt.xticks(range(10), class_names, rotation=45)

In [28]: np.argmax(predictions_single[0])

Out[28]: 9

file:///C:/Users/deshm/Downloads/DL3 (2).html 7/7