eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-05-28 14:19:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

WIP: Adding a constraint

Browse source
This commit is contained in:
Jean-Marc Valin 2020-12-24 02:50:20 -05:00
parent c045702e51
commit 1657bae024
2 changed files with 24 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

22
dnn/training_tf2/lpcnet.py
View file

@ -29,6 +29,7 @@ import math
from tensorflow.keras.models import Model from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, GRU, Dense, Embedding, Reshape, Concatenate, Lambda, Conv1D, Multiply, Add, Bidirectional, MaxPooling1D, Activation from tensorflow.keras.layers import Input, GRU, Dense, Embedding, Reshape, Concatenate, Lambda, Conv1D, Multiply, Add, Bidirectional, MaxPooling1D, Activation
from tensorflow.keras import backend as K from tensorflow.keras import backend as K
from tensorflow.keras.constraints import Constraint
from tensorflow.keras.initializers import Initializer from tensorflow.keras.initializers import Initializer
from tensorflow.keras.callbacks import Callback from tensorflow.keras.callbacks import Callback
from mdense import MDense from mdense import MDense
@ -115,6 +116,21 @@ class PCMInit(Initializer):
'seed': self.seed 'seed': self.seed
} }
class WeightClip(Constraint):
'''Clips the weights incident to each hidden unit to be inside a range
'''
def __init__(self, c=2):
self.c = c
def __call__(self, p):
return K.clip(p, -self.c, self.c)
def get_config(self):
return {'name': self.__class__.__name__,
'c': self.c}
constraint = WeightClip(0.999)
def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features = 38, training=False, adaptation=False): def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features = 38, training=False, adaptation=False):
pcm = Input(shape=(None, 3)) pcm = Input(shape=(None, 3))
feat = Input(shape=(None, nb_used_features)) feat = Input(shape=(None, nb_used_features))
@ -142,8 +158,10 @@ def new_lpcnet_model(rnn_units1=384, rnn_units2=16, nb_used_features = 38, train
rep = Lambda(lambda x: K.repeat_elements(x, frame_size, 1)) rep = Lambda(lambda x: K.repeat_elements(x, frame_size, 1))
rnn = GRU(rnn_units1, return_sequences=True, return_state=True, recurrent_activation="sigmoid", reset_after='true', name='gru_a') 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') recurrent_constraint = constraint)
rnn2 = GRU(rnn_units2, return_sequences=True, return_state=True, recurrent_activation="sigmoid", reset_after='true', name='gru_b',
kernel_constraint=constraint)
rnn_in = Concatenate()([cpcm, rep(cfeat)]) rnn_in = Concatenate()([cpcm, rep(cfeat)])
md = MDense(pcm_levels, activation='softmax', name='dual_fc') md = MDense(pcm_levels, activation='softmax', name='dual_fc')

7
dnn/training_tf2/train_lpcnet.py
View file

@ -102,14 +102,15 @@ del pred
del in_exc del in_exc
# dump models to disk as we go # dump models to disk as we go
checkpoint = ModelCheckpoint('lpcnet32v_384_10_G16_{epoch:02d}.h5') checkpoint = ModelCheckpoint('lpcnet32y_384_10_G16_{epoch:02d}.h5')
#Set this to True to adapt an existing model (e.g. on new data) #Set this to True to adapt an existing model (e.g. on new data)
adaptation = False adaptation = False
model.load_weights('lpcnet32v_384_10_G16_00.h5')
if adaptation: if adaptation:
#Adapting from an existing model #Adapting from an existing model
model.load_weights('lpcnet24c_384_10_G16_120.h5') model.load_weights('lpcnet32v_384_10_G16_100.h5')
sparsify = lpcnet.Sparsify(0, 0, 1, (0.05, 0.05, 0.2)) sparsify = lpcnet.Sparsify(0, 0, 1, (0.05, 0.05, 0.2))
lr = 0.0001 lr = 0.0001
decay = 0 decay = 0
@ -120,5 +121,5 @@ else:
decay = 5e-5 decay = 5e-5
model.compile(optimizer=Adam(lr, decay=decay, beta_2=0.99), loss='sparse_categorical_crossentropy') model.compile(optimizer=Adam(lr, decay=decay, beta_2=0.99), loss='sparse_categorical_crossentropy')
model.save_weights('lpcnet32v_384_10_G16_00.h5'); model.save_weights('lpcnet32y_384_10_G16_00.h5');
model.fit([in_data, features, periods], out_exc, batch_size=batch_size, epochs=nb_epochs, validation_split=0.0, callbacks=[checkpoint, sparsify]) model.fit([in_data, features, periods], out_exc, batch_size=batch_size, epochs=nb_epochs, validation_split=0.0, callbacks=[checkpoint, sparsify])