shithub: opus

Info  •  Files  •  Log  •  Branches

More meaningful names

--- a/dnn/dump_lpcnet.py

+++ b/dnn/dump_lpcnet.py

@@ -32,7 +32,7 @@

 def dump_layer_ignore(self, f, hf):

     print("ignoring layer " + self.name + " of type " + self.__class__.__name__)

-    False

+    return False

 Layer.dump_layer = dump_layer_ignore

 def dump_gru_layer(self, f, hf):

@@ -55,7 +55,7 @@

             .format(name, name, name, name, weights[0].shape[0], weights[0].shape[1]//3, activation, reset_after))

     hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[1]//3))

     hf.write('extern const GRULayer {};\n\n'.format(name));

-    True

+    return True

 CuDNNGRU.dump_layer = dump_gru_layer

 GRU.dump_layer = dump_gru_layer

@@ -74,7 +74,7 @@

             .format(name, name, name, weights[0].shape[0], weights[0].shape[1], activation))

     hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[1]))

     hf.write('extern const DenseLayer {};\n\n'.format(name));

-    False

+    return False

 Dense.dump_layer = dump_dense_layer

 def dump_mdense_layer(self, f, hf):

@@ -93,7 +93,7 @@

             .format(name, name, name, name, weights[0].shape[0], weights[0].shape[1], activation))

     hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[0]))

     hf.write('extern const MDenseLayer {};\n\n'.format(name));

-    False

+    return False

 MDense.dump_layer = dump_mdense_layer

--- a/dnn/lpcnet.py

+++ b/dnn/lpcnet.py

@@ -94,12 +94,12 @@

     dec_state1 = Input(shape=(rnn_units1,))

     dec_state2 = Input(shape=(rnn_units2,))

-    fconv1 = Conv1D(128, 3, padding='same', activation='tanh')

-    fconv2 = Conv1D(102, 3, padding='same', activation='tanh')

+    fconv1 = Conv1D(128, 3, padding='same', activation='tanh', name='feature_conv1')

+    fconv2 = Conv1D(102, 3, padding='same', activation='tanh', name='feature_conv2')

-    embed = Embedding(256, embed_size, embeddings_initializer=PCMInit())

+    embed = Embedding(256, embed_size, embeddings_initializer=PCMInit(), name='embed_sig')

     cpcm = Reshape((-1, embed_size*2))(embed(pcm))

-    embed2 = Embedding(256, embed_size, embeddings_initializer=PCMInit())

+    embed2 = Embedding(256, embed_size, embeddings_initializer=PCMInit(), name='embed_exc')

     cexc = Reshape((-1, embed_size))(embed2(exc))

     pembed = Embedding(256, 64)

@@ -107,8 +107,8 @@

     cfeat = fconv2(fconv1(cat_feat))

-    fdense1 = Dense(128, activation='tanh')

-    fdense2 = Dense(128, activation='tanh')

+    fdense1 = Dense(128, activation='tanh', name='feature_dense1')

+    fdense2 = Dense(128, activation='tanh', name='feature_dense2')

     cfeat = Add()([cfeat, cat_feat])

     cfeat = fdense2(fdense1(cfeat))

@@ -115,10 +115,10 @@

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

-    rnn = CuDNNGRU(rnn_units1, return_sequences=True, return_state=True)

-    rnn2 = CuDNNGRU(rnn_units2, return_sequences=True, return_state=True)

+    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')

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

-    md = MDense(pcm_levels, activation='softmax')

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

     gru_out1, _ = rnn(rnn_in)

     gru_out2, _ = rnn2(Concatenate()([gru_out1, rep(cfeat)]))

     ulaw_prob = md(gru_out2)

-- 

⑨