/
keras_train.py
101 lines (79 loc) · 2.82 KB
/
keras_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
import tensorflow as tf
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from tensorflow import keras
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'
def preprocess(x, y):
# [0-255] => [-1~1]
x = 2 * tf.cast(x, dtype=tf.float32) / 255. - 1
y = tf.cast(y, dtype=tf.int32)
return x, y
batchsz = 128
(x, y), (x_val, y_val) = datasets.cifar10.load_data()
y = tf.squeeze(y)
y_val = tf.squeeze(y_val)
y = tf.one_hot(y, depth=10) # [50k, 10]
y_val = tf.one_hot(y_val, depth=10) # [10k, 10]
print('datasets: ', x.shape, y.shape, x_val.shape, y_val.shape, x.min(), x.max())
train_db = tf.data.Dataset.from_tensor_slices((x, y))
train_db = train_db.map(preprocess).shuffle(10000).batch(batchsz)
test_db = tf.data.Dataset.from_tensor_slices((x_val, y_val))
test_db = test_db.map(preprocess).batch(batchsz)
sample = next(iter(train_db))
print('batch: ', sample[0].shape, sample[1].shape)
class MyDense(layers.Layer):
# to replace standard layers.Dense()
def __init__(self, inp_dim, outp_dim):
super(MyDense, self).__init__()
self.kernel = self.add_weight('w', [inp_dim, outp_dim])
# self.bias=self.add_weight('b',[outp_dim])
def call(self, inputs, training=None):
x = inputs @ self.kernel
return x
class MyNetwork(tf.keras.Model):
def __init__(self):
super(MyNetwork, self).__init__()
self.fc1 = MyDense(32 * 32 * 3, 256)
self.fc2 = MyDense(256, 128)
self.fc3 = MyDense(128, 64)
self.fc4 = MyDense(64, 32)
self.fc5 = MyDense(32, 10)
def call(self, inputs, training=None):
"""
:param inputs: [b, 32, 32, 3]
:param training:
:return:
"""
x = tf.reshape(inputs, [-1, 32 * 32 * 3])
# [b,32*32*3] => [b, 256]
x = self.fc1(x)
x = tf.nn.relu(x)
# [b, 256] => [b, 128]
x = self.fc2(x)
x = tf.nn.relu(x)
# [b, 128] => [b, 64]
x = self.fc3(x)
x = tf.nn.relu(x)
# [b, 63] => [b, 32]
x = self.fc4(x)
x = tf.nn.relu(x)
# [b, 32] => [b, 10]
x = self.fc5(x)
return x
network = MyNetwork()
network.compile(optimizer=optimizers.Adam(lr=1e-3),
loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
network.fit(train_db, epochs=15, validation_data=test_db, validation_freq=1)
network.evaluate(test_db)
network.save_weights('ckpt/weight.ckpt')
del network
print('save to weight.ckpt')
network = MyNetwork()
network.compile(optimizer=optimizers.Adam(lr=1e-3),
loss=tf.losses.CategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
network.load_weights('ckpt/weight.ckpt')
print('loaded weight from file.')
network.evaluate(test_db)