testadmin
/
Parakeet
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

update for deepvoice3, fix weight norm

This commit is contained in:
chenfeiyu 2020-05-06 08:36:43 +00:00
parent 8505805dad
commit ff1d66ea94
4 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
examples/deepvoice3/train.py
View File

@ -196,8 +196,8 @@ if __name__ == "__main__":
beta1,
beta2,
epsilon=epsilon,
parameter_list=dv3.parameters())
gradient_clipper = fluid.dygraph_grad_clip.GradClipByGlobalNorm(0.1)
parameter_list=dv3.parameters(),
grad_clip=fluid.clip.GradientClipByGlobalNorm(0.1))
# generation
synthesis_config = config["synthesis"]
@ -258,15 +258,19 @@ if __name__ == "__main__":
text_lengths, frames)
l = losses["loss"]
l.backward()
# record learning rate before updating
writer.add_scalar("learning_rate",
optim._learning_rate.step().numpy(), global_step)
optim.minimize(l, grad_clip=gradient_clipper)
optim.minimize(l)
optim.clear_gradients()
# ==================all kinds of tedious things=================
# record step loss into tensorboard
step_loss = {k: v.numpy()[0] for k, v in losses.items()}
step_loss = {
k: v.numpy()[0]
for k, v in losses.items() if v is not None
}
tqdm.tqdm.write("global_step: {}\tloss: {}".format(
global_step, step_loss["loss"]))
for k, v in step_loss.items():

4
parakeet/models/deepvoice3/loss.py
View File

@ -262,7 +262,7 @@ class TTSLoss(object):
if compute_lin_loss:
lin_hyp = lin_hyp[:, :-self.time_shift, :]
lin_ref = lin_ref[:, self.time_shift:, :]
lin_mask = lin_mask[:, self.time_shift:, :]
lin_mask = lin_mask[:, self.time_shift:]
lin_l1_loss = self.l1_loss(
lin_hyp, lin_ref, lin_mask, priority_bin=self.priority_bin)
lin_bce_loss = self.binary_divergence(lin_hyp, lin_ref, lin_mask)
@ -273,7 +273,7 @@ class TTSLoss(object):
if compute_mel_loss:
mel_hyp = mel_hyp[:, :-self.time_shift, :]
mel_ref = mel_ref[:, self.time_shift:, :]
mel_mask = mel_mask[:, self.time_shift:, :]
mel_mask = mel_mask[:, self.time_shift:]
mel_l1_loss = self.l1_loss(mel_hyp, mel_ref, mel_mask)
mel_bce_loss = self.binary_divergence(mel_hyp, mel_ref, mel_mask)
# print("=====>", mel_l1_loss.numpy()[0], mel_bce_loss.numpy()[0])

6
parakeet/models/deepvoice3/position_embedding.py
View File

@ -31,8 +31,10 @@ def compute_position_embedding(radians, speaker_position_rate):
"""
_, embed_dim = radians.shape
batch_size = speaker_position_rate.shape[0]
speaker_position_rate = F.unsqueeze(speaker_position_rate, [1, 2])
scaled_radians = speaker_position_rate * radians
scaled_radians = F.elementwise_mul(
F.expand(F.unsqueeze(radians, [0]), [batch_size, 1, 1]),
speaker_position_rate,
axis=0)
odd_mask = (np.arange(embed_dim) % 2).astype(np.float32)
odd_mask = dg.to_variable(odd_mask)

6
parakeet/modules/weight_norm.py
View File

@ -84,13 +84,15 @@ class WeightNormWrapper(dg.Layer):
w_v,
self.create_parameter(
shape=original_weight.shape, dtype=original_weight.dtype))
F.assign(original_weight, getattr(self, w_v))
with dg.no_grad():
F.assign(original_weight, getattr(self, w_v))
delattr(layer, param_name)
temp = norm_except(getattr(self, w_v), self.dim, self.power)
self.add_parameter(
w_g, self.create_parameter(
shape=temp.shape, dtype=temp.dtype))
F.assign(temp, getattr(self, w_g))
with dg.no_grad():
F.assign(temp, getattr(self, w_g))
# also set this when setting up
setattr(self.layer, self.param_name,