shithub: opus

Info  •  Files  •  Log  •  Branches

Using non-cudnn version of the GRU for the weights

Not sure how the layout of the CuDNN version is

--- a/dnn/dump_lpcnet.py

+++ b/dnn/dump_lpcnet.py

@@ -47,8 +47,8 @@

         activation = self.activation.__name__.upper()

     else:

         activation = 'TANH'

-    if hasattr(self, 'reset_after'):

-        reset_after = self.reset_after

+    if hasattr(self, 'reset_after') and not self.reset_after:

+        reset_after = 0

     else:

         reset_after = 1

     f.write('const GRULayer {} = {{\n   {}_bias,\n   {}_weights,\n   {}_recurrent_weights,\n   {}, {}, ACTIVATION_{}, {}\n}};\n\n'

@@ -97,7 +97,7 @@

 MDense.dump_layer = dump_mdense_layer

-model, _, _ = lpcnet.new_lpcnet_model(rnn_units1=640)

+model, _, _ = lpcnet.new_lpcnet_model(rnn_units1=640, use_gpu=False)

 model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])

 #model.summary()

--- a/dnn/lpcnet.py

+++ b/dnn/lpcnet.py

@@ -2,7 +2,7 @@

 import math

 from keras.models import Model

-from keras.layers import Input, LSTM, CuDNNGRU, Dense, Embedding, Reshape, Concatenate, Lambda, Conv1D, Multiply, Add, Bidirectional, MaxPooling1D, Activation

+from keras.layers import Input, GRU, CuDNNGRU, Dense, Embedding, Reshape, Concatenate, Lambda, Conv1D, Multiply, Add, Bidirectional, MaxPooling1D, Activation

 from keras import backend as K

 from keras.initializers import Initializer

 from keras.callbacks import Callback

@@ -85,7 +85,7 @@

             'seed': self.seed

         }

-def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features = 38):

+def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features = 38, use_gpu=True):

     pcm = Input(shape=(None, 2))

     exc = Input(shape=(None, 1))

     feat = Input(shape=(None, nb_used_features))

@@ -115,8 +115,13 @@

     rep = Lambda(lambda x: K.repeat_elements(x, 160, 1))

-    rnn = CuDNNGRU(rnn_units1, return_sequences=True, return_state=True, name='gru_a')

-    rnn2 = CuDNNGRU(rnn_units2, return_sequences=True, return_state=True, name='gru_b')

+    if use_gpu:

+        rnn = CuDNNGRU(rnn_units1, return_sequences=True, return_state=True, name='gru_a')

+        rnn2 = CuDNNGRU(rnn_units2, return_sequences=True, return_state=True, name='gru_b')

+    else:

+        rnn = GRU(rnn_units1, return_sequences=True, return_state=True, recurrent_activation="sigmoid", reset_after='true', name='gru_a')

+        rnn2 = GRU(rnn_units2, return_sequences=True, return_state=True, recurrent_activation="sigmoid", reset_after='true', name='gru_b')

+

     rnn_in = Concatenate()([cpcm, cexc, rep(cfeat)])

     md = MDense(pcm_levels, activation='softmax', name='dual_fc')

     gru_out1, _ = rnn(rnn_in)

-- 

⑨