Onnowpurbo at 13:00, 24 June 2025

2025-06-24T13:00:49Z

Onnowpurbo: Created page with " #!/usr/bin/env python2 # -- coding: utf-8 -- """ Created on Sat Aug 10 07:51:56 2019 https://towardsdatascience.com/image-classification-in-10-minutes-with-mnist-data..."

2019-08-10T01:08:46Z

Created page with " #!/usr/bin/env python2 # -*- coding: utf-8 -*- """ Created on Sat Aug 10 07:51:56 2019 https://towardsdatascience.com/image-classification-in-10-minutes-with-mnist-data..."

New page

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Sat Aug 10 07:51:56 2019

https://towardsdatascience.com/image-classification-in-10-minutes-with-mnist-dataset-54c35b77a38d
"""

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

#
import matplotlib.pyplot as plt
image_index = 7777 # You may select anything up to 60,000
print(y_train[image_index]) # The label is 8
plt.imshow(x_train[image_index], cmap='Greys')

x_train.shape

# Reshaping the array to 4-dims so that it can work with the Keras API
x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
input_shape = (28, 28, 1)
# Making sure that the values are float so that we can get decimal points after division
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
# Normalizing the RGB codes by dividing it to the max RGB value.
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print('Number of images in x_train', x_train.shape[0])
print('Number of images in x_test', x_test.shape[0])

# Importing the required Keras modules containing model and layers
from keras.models import Sequential
from keras.layers import Dense, Conv2D, Dropout, Flatten, MaxPooling2D
# Creating a Sequential Model and adding the layers
model = Sequential()
model.add(Conv2D(28, kernel_size=(3,3), input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten()) # Flattening the 2D arrays for fully connected layers
model.add(Dense(128, activation=tf.nn.relu))
model.add(Dropout(0.2))
model.add(Dense(10,activation=tf.nn.softmax))

model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(x=x_train,y=y_train, epochs=10)

# test / evaluate model
model.evaluate(x_test, y_test)

# test image classification
image_index = 100
plt.imshow(x_test[image_index].reshape(28, 28),cmap='Greys')
pred = model.predict(x_test[image_index].reshape(1, img_rows, img_cols, 1))
print(pred.argmax())

==Pranala Menarik==

* [[Keras]]

@@ Line 56: / Line 56: @@
   image_index = 100
   plt.imshow(x_test[image_index].reshape(28, 28),cmap='Greys')
-  pred = model.predict(x_test[image_index].reshape(1, img_rows, img_cols, 1))
+  pred = model.predict(x_test[image_index].reshape(1, 28, 28, 1))
   print(pred.argmax())

Keras Image Classification - Revision history

Onnowpurbo at 13:00, 24 June 2025

Onnowpurbo: Created page with " #!/usr/bin/env python2 # -*- coding: utf-8 -*- """ Created on Sat Aug 10 07:51:56 2019 https://towardsdatascience.com/image-classification-in-10-minutes-with-mnist-data..."

Onnowpurbo: Created page with " #!/usr/bin/env python2 # -- coding: utf-8 -- """ Created on Sat Aug 10 07:51:56 2019 https://towardsdatascience.com/image-classification-in-10-minutes-with-mnist-data..."