Keras training code

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")