training/rnn_train.py

#!/usr/bin/python

from __future__ import print_function

import keras
from keras.models import Sequential
from keras.models import Model
from keras.layers import Input
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import GRU
from keras.layers import SimpleRNN
from keras.layers import Dropout
from keras.layers import concatenate
from keras import losses
from keras import regularizers
import h5py

from keras import backend as K
import numpy as np

#import tensorflow as tf
#from keras.backend.tensorflow_backend import set_session
#config = tf.ConfigProto()
#config.gpu_options.per_process_gpu_memory_fraction = 0.42
#set_session(tf.Session(config=config))


def my_crossentropy(y_true, y_pred):
    return K.mean(2*K.abs(y_true-0.5) * K.binary_crossentropy(y_pred, y_true), axis=-1)

def mymask(y_true):
    return K.minimum(y_true+1., 1.)

def msse(y_true, y_pred):
    return K.mean(mymask(y_true) * K.square(K.sqrt(y_pred) - K.sqrt(y_true)), axis=-1)

def mycost(y_true, y_pred):
    return K.mean(mymask(y_true) * (K.square(K.sqrt(y_pred) - K.sqrt(y_true)) + 0.01*K.binary_crossentropy(y_pred, y_true)), axis=-1)

def my_accuracy(y_true, y_pred):
    return K.mean(2*K.abs(y_true-0.5) * K.equal(y_true, K.round(y_pred)), axis=-1)

reg = 0.000001

print('Build model...')
main_input = Input(shape=(None, 42), name='main_input')
tmp = Dense(24, activation='tanh', name='input_dense')(main_input)
vad_gru = GRU(24, activation='tanh', recurrent_activation='sigmoid', return_sequences=True, name='vad_gru', kernel_regularizer=regularizers.l2(reg), recurrent_regularizer=regularizers.l2(reg))(tmp)
vad_output = Dense(1, activation='sigmoid', name='vad_output')(vad_gru)
noise_input = keras.layers.concatenate([tmp, vad_gru, main_input])
noise_gru = GRU(48, activation='relu', recurrent_activation='sigmoid', return_sequences=True, name='noise_gru', kernel_regularizer=regularizers.l2(reg), recurrent_regularizer=regularizers.l2(reg))(noise_input)
denoise_input = keras.layers.concatenate([vad_gru, noise_gru, main_input])

denoise_gru = GRU(96, activation='tanh', recurrent_activation='sigmoid', return_sequences=True, name='denoise_gru', kernel_regularizer=regularizers.l2(reg), recurrent_regularizer=regularizers.l2(reg))(denoise_input)

denoise_output = Dense(22, activation='sigmoid', name='denoise_output')(denoise_gru)

model = Model(inputs=main_input, outputs=[denoise_output, vad_output])

model.compile(loss=[mycost, my_crossentropy],
              metrics=[msse],
              optimizer='adam', loss_weights=[10, 0.5])


batch_size = 32

print('Loading data...')
with h5py.File('denoise_data6.h5', 'r') as hf:
    all_data = hf['data'][:]
print('done.')

window_size = 2000

nb_sequences = len(all_data)//window_size
print(nb_sequences, ' sequences')
x_train = all_data[:nb_sequences*window_size, :42]
x_train = np.reshape(x_train, (nb_sequences, window_size, 42))

y_train = np.copy(all_data[:nb_sequences*window_size, 42:64])
y_train = np.reshape(y_train, (nb_sequences, window_size, 22))

noise_train = np.copy(all_data[:nb_sequences*window_size, 64:86])
noise_train = np.reshape(noise_train, (nb_sequences, window_size, 22))

vad_train = np.copy(all_data[:nb_sequences*window_size, 86:87])
vad_train = np.reshape(vad_train, (nb_sequences, window_size, 1))

all_data = 0;
#x_train = x_train.astype('float32')
#y_train = y_train.astype('float32')

print(len(x_train), 'train sequences. x shape =', x_train.shape, 'y shape = ', y_train.shape)

print('Train...')
model.fit(x_train, [y_train, vad_train],
          batch_size=batch_size,
          epochs=60,
          validation_split=0.1)
model.save("newweights6a2a.hdf5")