shithub: opus

Info  •  Files  •  Log  •  Branches

stashing stuff here

--- a/dnn/denoise.c

+++ b/dnn/denoise.c

@@ -577,6 +577,7 @@

       return 0;

     }

     for (i=0;i<FRAME_SIZE;i++) x[i] = tmp[i];

+    for (i=0;i<FRAME_SIZE;i++) x[i] += rand()/(float)RAND_MAX - .5;

     for (i=0;i<FRAME_SIZE;i++) E += tmp[i]*(float)tmp[i];

     biquad(x, mem_hp_x, x, b_hp, a_hp, FRAME_SIZE);

     preemphasis(x, &mem_preemph, x, PREEMPHASIS, FRAME_SIZE);

--- a/dnn/lpcnet.py

+++ b/dnn/lpcnet.py

@@ -12,7 +12,7 @@

 rnn_units=512

 pcm_bits = 8

 pcm_levels = 2**pcm_bits

-nb_used_features = 37

+nb_used_features = 38

 def new_wavernn_model():

@@ -22,11 +22,11 @@

     dec_feat = Input(shape=(None, 32))

     dec_state = Input(shape=(rnn_units,))

-    conv1 = Conv1D(16, 7, padding='causal')

-    pconv1 = Conv1D(16, 5, padding='same')

-    pconv2 = Conv1D(16, 5, padding='same')

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

-    fconv2 = Conv1D(32, 3, padding='same')

+    conv1 = Conv1D(16, 7, padding='causal', activation='tanh')

+    pconv1 = Conv1D(16, 5, padding='same', activation='tanh')

+    pconv2 = Conv1D(16, 5, padding='same', activation='tanh')

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

+    fconv2 = Conv1D(32, 3, padding='same', activation='tanh')

     if False:

         cpcm = conv1(pcm)

@@ -40,17 +40,17 @@

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

     rnn = CuDNNGRU(rnn_units, return_sequences=True, return_state=True)

-    rnn_in = Concatenate()([cpcm, cpitch, rep(cfeat)])

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

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

     gru_out, state = rnn(rnn_in)

     ulaw_prob = md(gru_out)

-    model = Model([pcm, pitch, feat], ulaw_prob)

+    model = Model([pcm, feat], ulaw_prob)

     encoder = Model(feat, cfeat)

-    dec_rnn_in = Concatenate()([cpcm, cpitch, dec_feat])

+    dec_rnn_in = Concatenate()([cpcm, dec_feat])

     dec_gru_out, state = rnn(dec_rnn_in, initial_state=dec_state)

     dec_ulaw_prob = md(dec_gru_out)

-    decoder = Model([pcm, pitch, dec_feat, dec_state], [dec_ulaw_prob, state])

+    decoder = Model([pcm, dec_feat, dec_state], [dec_ulaw_prob, state])

     return model, encoder, decoder

--- a/dnn/test_lpcnet.py

+++ b/dnn/test_lpcnet.py

@@ -47,7 +47,7 @@

 out_data = np.reshape(data, (nb_frames*pcm_chunk_size, 1))

-model.load_weights('lpcnet1i_30.h5')

+model.load_weights('lpcnet3a_21.h5')

 order = 16

@@ -61,7 +61,7 @@

     cfeat = enc.predict(features[c:c+1, :, :nb_used_features])

     for fr in range(1, feature_chunk_size):

         f = c*feature_chunk_size + fr

-        a = features[c, fr, nb_used_features+1:]

+        a = features[c, fr, nb_used_features:]

         #print(a)

         gain = 1.;

@@ -69,9 +69,10 @@

         period = period - 4

         for i in range(frame_size):

             pitch[0, 0, 0] = exc[f*frame_size + i - period, 0]

-            fexc[0, 0, 0] = exc[f*frame_size + i - 1]

+            fexc[0, 0, 0] = 2*exc[f*frame_size + i - 1]

+            #fexc[0, 0, 0] = in_data[f*frame_size + i, 0]

             #print(cfeat.shape)

-            p, state = dec.predict([fexc, pitch, cfeat[:, fr:fr+1, :], state])

+            p, state = dec.predict([fexc, cfeat[:, fr:fr+1, :], state])

             p = p/(1e-5 + np.sum(p))

             #print(np.sum(p))

             iexc[0, 0, 0] = np.argmax(np.random.multinomial(1, p[0,0,:], 1))-128

--- a/dnn/train_lpcnet.py

+++ b/dnn/train_lpcnet.py

@@ -13,13 +13,13 @@

 import tensorflow as tf

 from keras.backend.tensorflow_backend import set_session

 config = tf.ConfigProto()

-config.gpu_options.per_process_gpu_memory_fraction = 0.28

+config.gpu_options.per_process_gpu_memory_fraction = 0.44

 set_session(tf.Session(config=config))

 nb_epochs = 40

 batch_size = 64

-model = lpcnet.new_wavernn_model()

+model, enc, dec = lpcnet.new_wavernn_model()

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

 model.summary()

@@ -63,8 +63,8 @@

 # f.create_dataset('data', data=in_data[:50000, :, :])

 # f.create_dataset('feat', data=features[:50000, :, :])

-checkpoint = ModelCheckpoint('lpcnet1k_{epoch:02d}.h5')

+checkpoint = ModelCheckpoint('lpcnet3b_{epoch:02d}.h5')

 #model.load_weights('wavernn1c_01.h5')

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

-model.fit([in_data, in_pitch, features], out_data, batch_size=batch_size, epochs=30, validation_split=0.2, callbacks=[checkpoint])

+model.compile(optimizer=Adam(0.001, amsgrad=True, decay=2e-4), loss='sparse_categorical_crossentropy', metrics=['sparse_categorical_accuracy'])

+model.fit([in_data, features], out_data, batch_size=batch_size, epochs=30, validation_split=0.2, callbacks=[checkpoint])

-- 

⑨