|
import tensorflow as tf |
|
from typing import Tuple |
|
|
|
def _inception_module( |
|
input_tensor, |
|
stride=1, |
|
activation="linear", |
|
use_bottleneck=True, |
|
kernel_size=40, |
|
bottleneck_size=32, |
|
nb_filters=32, |
|
): |
|
|
|
if use_bottleneck and int(input_tensor.shape[-1]) > 1: |
|
input_inception = tf.keras.layers.Conv1D( |
|
filters=bottleneck_size, |
|
kernel_size=1, |
|
padding="same", |
|
activation=activation, |
|
use_bias=False, |
|
)(input_tensor) |
|
else: |
|
input_inception = input_tensor |
|
|
|
|
|
kernel_size_s = [kernel_size // (2**i) for i in range(3)] |
|
|
|
conv_list = [] |
|
|
|
for i in range(len(kernel_size_s)): |
|
conv_list.append( |
|
tf.keras.layers.Conv1D( |
|
filters=nb_filters, |
|
kernel_size=kernel_size_s[i], |
|
strides=stride, |
|
padding="same", |
|
activation=activation, |
|
use_bias=False, |
|
)(input_inception) |
|
) |
|
|
|
max_pool_1 = tf.keras.layers.MaxPool1D(pool_size=3, strides=stride, padding="same")( |
|
input_tensor |
|
) |
|
|
|
conv_6 = tf.keras.layers.Conv1D( |
|
filters=nb_filters, |
|
kernel_size=1, |
|
padding="same", |
|
activation=activation, |
|
use_bias=False, |
|
)(max_pool_1) |
|
|
|
conv_list.append(conv_6) |
|
|
|
x = tf.keras.layers.Concatenate(axis=2)(conv_list) |
|
x = tf.keras.layers.BatchNormalization()(x) |
|
x = tf.keras.layers.Activation(activation="relu")(x) |
|
return x |
|
|
|
|
|
def _shortcut_layer(input_tensor, out_tensor): |
|
shortcut_y = tf.keras.layers.Conv1D( |
|
filters=int(out_tensor.shape[-1]), kernel_size=1, padding="same", use_bias=False |
|
)(input_tensor) |
|
shortcut_y = tf.keras.layers.BatchNormalization()(shortcut_y) |
|
|
|
x = tf.keras.layers.Add()([shortcut_y, out_tensor]) |
|
x = tf.keras.layers.Activation("relu")(x) |
|
return x |
|
|
|
|
|
def build_age_model( |
|
input_shape: Tuple[int, int], |
|
nb_classes: int, |
|
depth: int = 6, |
|
use_residual: bool = True, |
|
)-> tf.keras.models.Model: |
|
""" |
|
Model proposed by HI Fawas et al 2019 "Finding AlexNet for Time Series Classification - InceptionTime" |
|
""" |
|
input_layer = tf.keras.layers.Input(input_shape) |
|
|
|
x = input_layer |
|
input_res = input_layer |
|
|
|
for d in range(depth): |
|
|
|
x = _inception_module(x) |
|
|
|
if use_residual and d % 3 == 2: |
|
x = _shortcut_layer(input_res, x) |
|
input_res = x |
|
|
|
gap_layer = tf.keras.layers.GlobalAveragePooling1D()(x) |
|
|
|
output_layer = tf.keras.layers.Dense(units=nb_classes, activation="linear")( |
|
gap_layer |
|
) |
|
|
|
model = tf.keras.models.Model(inputs=input_layer, outputs=output_layer) |
|
model.compile( |
|
loss=tf.keras.losses.MeanAbsoluteError(), |
|
optimizer=tf.keras.optimizers.Adam(learning_rate=0.001), |
|
metrics=[tf.keras.metrics.MeanSquaredError()], |
|
) |
|
|
|
return model |
|
|
|
|
|
|
|
def build_gender_model( |
|
input_shape: Tuple[int, int], |
|
nb_classes: int, |
|
depth: int = 6, |
|
use_residual: bool = True, |
|
)-> tf.keras.models.Model: |
|
""" |
|
Model proposed by HI Fawas et al 2019 "Finding AlexNet for Time Series Classification - InceptionTime" |
|
""" |
|
input_layer = tf.keras.layers.Input(input_shape) |
|
|
|
x = input_layer |
|
input_res = input_layer |
|
|
|
for d in range(depth): |
|
|
|
x = _inception_module(x) |
|
|
|
if use_residual and d % 3 == 2: |
|
x = _shortcut_layer(input_res, x) |
|
input_res = x |
|
|
|
gap_layer = tf.keras.layers.GlobalAveragePooling1D()(x) |
|
|
|
output_layer = tf.keras.layers.Dense(units=nb_classes, activation="sigmoid")( |
|
gap_layer |
|
) |
|
|
|
model = tf.keras.models.Model(inputs=input_layer, outputs=output_layer) |
|
model.compile( |
|
loss=tf.keras.losses.BinaryCrossentropy(), |
|
optimizer=tf.keras.optimizers.Adam(learning_rate=0.001), |
|
metrics=[tf.keras.metrics.AUC(curve='ROC',name="AUROC")], |
|
) |
|
|
|
return model |
