diff options
-rwxr-xr-x | training/bin2hdf5.py | 13 | ||||
-rwxr-xr-x | training/rnn_train.py | 97 |
2 files changed, 110 insertions, 0 deletions
diff --git a/training/bin2hdf5.py b/training/bin2hdf5.py new file mode 100755 index 0000000..51dcbdf --- /dev/null +++ b/training/bin2hdf5.py @@ -0,0 +1,13 @@ +#!/usr/bin/python + +from __future__ import print_function + +import numpy as np +import h5py +import sys + +data = np.fromfile(sys.argv[1], dtype='float32'); +data = np.reshape(data, (int(sys.argv[2]), int(sys.argv[3]))); +h5f = h5py.File(sys.argv[4], 'w'); +h5f.create_dataset('data', data=data) +h5f.close() diff --git a/training/rnn_train.py b/training/rnn_train.py new file mode 100755 index 0000000..3917caf --- /dev/null +++ b/training/rnn_train.py @@ -0,0 +1,97 @@ +#!/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 msse(y_true, y_pred): + return K.mean(K.square(K.sqrt(y_pred) - K.sqrt(y_true)), axis=-1) + +def mycost(y_true, y_pred): + return K.mean(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 = 0.0001 + +print('Build model...') +main_input = Input(shape=(None, 42), name='main_input') +tmp = Dense(12, activation='tanh', name='input_dense')(main_input) +vad_gru = GRU(12, 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(128, 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 = 256 + +print('Loading data...') +with h5py.File('denoise_data4.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=300, + validation_split=0.1) +model.save("newweights3c.hdf5") |