InceptionTime/classifiers/inception.py at 69f3edc6e754e79b8fc00adef1e20c65e370fab4 · hfawaz/InceptionTime · GitHub

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
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
import tensorflow.keras as keras
import tensorflow as tf
import numpy as np
import time

from utils.utils import save_logs
from utils.utils import calculate_metrics
from utils.utils import save_test_duration


class Classifier_INCEPTION:

    def __init__(self, output_directory, input_shape, nb_classes, verbose=False, build=True, batch_size=64, lr=0.001,
                 nb_filters=32, use_residual=True, use_bottleneck=True, depth=6, kernel_size=41, nb_epochs=1500):

        self.output_directory = output_directory

        self.nb_filters = nb_filters
        self.use_residual = use_residual
        self.use_bottleneck = use_bottleneck
        self.depth = depth
        self.kernel_size = kernel_size - 1
        self.callbacks = None
        self.batch_size = batch_size
        self.bottleneck_size = 32
        self.nb_epochs = nb_epochs
        self.lr = lr
        self.verbose = verbose

        if build == True:
            self.model = self.build_model(input_shape, nb_classes)
            if (verbose == True):
                self.model.summary()
            self.model.save_weights(self.output_directory + 'model_init.hdf5')

    def _inception_module(self, input_tensor, stride=1, activation='linear'):

        if self.use_bottleneck and int(input_tensor.shape[-1]) > self.bottleneck_size:
            input_inception = keras.layers.Conv1D(filters=self.bottleneck_size, kernel_size=1,
                                                  padding='same', activation=activation, use_bias=False)(input_tensor)
        else:
            input_inception = input_tensor

        # kernel_size_s = [3, 5, 8, 11, 17]
        kernel_size_s = [self.kernel_size // (2 ** i) for i in range(3)]

        conv_list = []

        for i in range(len(kernel_size_s)):
            conv_list.append(keras.layers.Conv1D(filters=self.nb_filters, kernel_size=kernel_size_s[i],
                                                 strides=stride, padding='same', activation=activation, use_bias=False)(
                input_inception))

        max_pool_1 = keras.layers.MaxPool1D(pool_size=3, strides=stride, padding='same')(input_tensor)

        conv_6 = keras.layers.Conv1D(filters=self.nb_filters, kernel_size=1,
                                     padding='same', activation=activation, use_bias=False)(max_pool_1)

        conv_list.append(conv_6)

        x = keras.layers.Concatenate(axis=2)(conv_list)
        x = keras.layers.BatchNormalization()(x)
        x = keras.layers.Activation(activation='relu')(x)
        return x

    def _shortcut_layer(self, input_tensor, out_tensor):
        shortcut_y = keras.layers.Conv1D(filters=int(out_tensor.shape[-1]), kernel_size=1,
                                         padding='same', use_bias=False)(input_tensor)
        shortcut_y = keras.layers.BatchNormalization()(shortcut_y)

        x = keras.layers.Add()([shortcut_y, out_tensor])
        x = keras.layers.Activation('relu')(x)
        return x

    def build_model(self, input_shape, nb_classes):
        input_layer = keras.layers.Input(input_shape)

        x = input_layer
        input_res = input_layer

        for d in range(self.depth):

            x = self._inception_module(x)

            if self.use_residual and d % 3 == 2:
                x = self._shortcut_layer(input_res, x)
                input_res = x

        gap_layer = keras.layers.GlobalAveragePooling1D()(x)

        output_layer = keras.layers.Dense(nb_classes, activation='softmax')(gap_layer)

        model = keras.models.Model(inputs=input_layer, outputs=output_layer)

        model.compile(loss='categorical_crossentropy', optimizer=keras.optimizers.Adam(self.lr),
                      metrics=['accuracy'])

        reduce_lr = keras.callbacks.ReduceLROnPlateau(monitor='loss', factor=0.5, patience=50,
                                                      min_lr=0.0001)

        file_path = self.output_directory + 'best_model.hdf5'

        model_checkpoint = keras.callbacks.ModelCheckpoint(filepath=file_path, monitor='loss',
                                                           save_best_only=True)

        self.callbacks = [reduce_lr, model_checkpoint]

        return model

    def fit(self, x_train, y_train, x_val, y_val, y_true):
        if not tf.test.is_gpu_available:
            print('error no gpu')
            exit()
        # x_val and y_val are only used to monitor the test loss and NOT for training

        if self.batch_size is None:
            mini_batch_size = int(min(x_train.shape[0] / 10, 16))
        else:
            mini_batch_size = self.batch_size

        start_time = time.time()

        hist = self.model.fit(x_train, y_train, batch_size=mini_batch_size, epochs=self.nb_epochs,
                              verbose=self.verbose, validation_data=(x_val, y_val), callbacks=self.callbacks)

        duration = time.time() - start_time

        self.model.save(self.output_directory + 'last_model.hdf5')

        y_pred = self.predict(x_val, y_true, x_train, y_train, y_val,
                              return_df_metrics=False)

        # save predictions
        np.save(self.output_directory + 'y_pred.npy', y_pred)

        # convert the predicted from binary to integer
        y_pred = np.argmax(y_pred, axis=1)

        df_metrics = save_logs(self.output_directory, hist, y_pred, y_true, duration)

        keras.backend.clear_session()

        return df_metrics

    def predict(self, x_test, y_true, x_train, y_train, y_test, return_df_metrics=True):
        start_time = time.time()
        model_path = self.output_directory + 'best_model.hdf5'
        model = keras.models.load_model(model_path)
        y_pred = model.predict(x_test, batch_size=self.batch_size)
        if return_df_metrics:
            y_pred = np.argmax(y_pred, axis=1)
            df_metrics = calculate_metrics(y_true, y_pred, 0.0)
            return df_metrics
        else:
            test_duration = time.time() - start_time
            save_test_duration(self.output_directory + 'test_duration.csv', test_duration)
            return y_pred