-
Notifications
You must be signed in to change notification settings - Fork 1
/
train.py
110 lines (76 loc) · 2.53 KB
/
train.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
from __future__ import absolute_import, division, print_function
# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow import keras
import os
# Helper libraries
import numpy as np
import matplotlib.pyplot as plt
# keras imports for the dataset and building our neural network
from keras.datasets import mnist
from keras.models import Sequential, load_model
from keras.layers.core import Dense, Dropout, Activation
from keras.utils import np_utils
# print(tf.__version__)
handwriting = keras.datasets.mnist
# print(train_images.shape)
model = Sequential()
model.add(Dense(512, input_shape=(784,)))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(10))
model.add(Activation('softmax'))
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# print("X_train shape", X_train.shape)
# print("y_train shape", y_train.shape)
# print("X_test shape", X_test.shape)
# print("y_test shape", y_test.shape)
# building the input vector from the 28x28 pixels
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
# print the final input shape ready for training
print("Train matrix shape", X_train.shape)
print("Test matrix shape", X_test.shape)
n_classes = 10
print("Shape before one-hot encoding: ", y_train.shape)
Y_train = np_utils.to_categorical(y_train, n_classes)
Y_test = np_utils.to_categorical(y_test, n_classes)
print("Shape after one-hot encoding: ", Y_train.shape)
model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')
model.summary()
history = model.fit(X_train, Y_train,
batch_size=128, epochs=20,
verbose=2,
validation_data=(X_test, Y_test))
save_dir = "./results/"
model_name = 'keras_mnist.h5'
if not os.path.exists(save_dir):
os.mkdir(save_dir)
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model at %s ' % model_path)
# plotting the metrics
fig = plt.figure()
plt.subplot(2,1,1)
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='lower right')
plt.subplot(2,1,2)
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper right')
plt.tight_layout()
fig