└── image classification


/image classification:
--------------------------------------------------------------------------------
 1 | import tensorflow as tf
 2 | from tensorflow import keras
 3 | from tensorflow.keras import datasets, layers, models
 4 | import matplotlib.pyplot as plt
 5 | %matplotlib inline
 6 | import numpy as np
 7 | 
 8 | 
 9 | (X_train, y_train) , (X_test, y_test) = keras.datasets.mnist.load_data()
10 | 
11 | X_train.shape
12 | 
13 | 
14 | X_test.shape
15 | 
16 | 
17 | X_train[0].shape
18 | 
19 | plt.matshow(X_train[0])
20 | 
21 | plt.matshow(X_train[0])
22 | 
23 | X_train = X_train / 255
24 | X_test = X_test / 255
25 | 
26 | model = keras.Sequential([
27 |     
28 |     layers.Conv2D(30, (3,3), activation='relu', input_shape=(28, 28, 1)),
29 |     layers.MaxPooling2D((2,2)),
30 |  
31 |     layers.Flatten(),
32 |     layers.Dense(100, activation='relu'),
33 |     keras.layers.Dense(10, activation='sigmoid')
34 | ])
35 | 
36 | 
37 | model.compile(optimizer='adam',
38 |               loss='sparse_categorical_crossentropy',
39 |               metrics=['accuracy'])
40 | 
41 | model.fit(X_train, y_train, epochs=5)
42 | 
43 | y_train[:5]
44 | 
45 | model.evaluate(X_test,y_test)
46 | 


--------------------------------------------------------------------------------