def train(model,
criterion,
optimizer,
optimizer_st,
scheduler,
ap,
global_step,
epoch,
amp,
speaker_mapping=None):
data_loader = setup_loader(ap,
model.decoder.r,
is_val=False,
verbose=(epoch == 0),
speaker_mapping=speaker_mapping)
model.train()
epoch_time = 0
keep_avg = KeepAverage()
if use_cuda:
batch_n_iter = int(
len(data_loader.dataset) / (c.batch_size * num_gpus))
else:
batch_n_iter = int(len(data_loader.dataset) / c.batch_size)
end_time = time.time()
c_logger.print_train_start()
for num_iter, data in enumerate(data_loader):
start_time = time.time()
# format data
text_input, text_lengths, mel_input, mel_lengths, linear_input, stop_targets, speaker_ids, speaker_embeddings, avg_text_length, avg_spec_length = format_data(
data, speaker_mapping)
loader_time = time.time() - end_time
global_step += 1
# setup lr
if c.noam_schedule:
scheduler.step()
optimizer.zero_grad()
if optimizer_st:
optimizer_st.zero_grad()
# forward pass model
if c.bidirectional_decoder or c.double_decoder_consistency:
decoder_output, postnet_output, alignments, stop_tokens, decoder_backward_output, alignments_backward = model(
text_input,
text_lengths,
mel_input,
mel_lengths,
speaker_ids=speaker_ids,
speaker_embeddings=speaker_embeddings)
else:
decoder_output, postnet_output, alignments, stop_tokens = model(
text_input,
text_lengths,
mel_input,
mel_lengths,
speaker_ids=speaker_ids,
speaker_embeddings=speaker_embeddings)
decoder_backward_output = None
alignments_backward = None
# set the [alignment] lengths wrt reduction factor for guided attention
if mel_lengths.max() % model.decoder.r != 0:
alignment_lengths = (
mel_lengths +
(model.decoder.r -
(mel_lengths.max() % model.decoder.r))) // model.decoder.r
else:
alignment_lengths = mel_lengths // model.decoder.r
# compute loss
loss_dict = criterion(postnet_output, decoder_output, mel_input,
linear_input, stop_tokens, stop_targets,
mel_lengths, decoder_backward_output, alignments,
alignment_lengths, alignments_backward,
text_lengths)
# backward pass
if amp is not None:
with amp.scale_loss(loss_dict['loss'], optimizer) as scaled_loss:
scaled_loss.backward()
else:
loss_dict['loss'].backward()
optimizer, current_lr = adam_weight_decay(optimizer)
if amp:
amp_opt_params = amp.master_params(optimizer)
else:
amp_opt_params = None
grad_norm, _ = check_update(model,
c.grad_clip,
ignore_stopnet=True,
amp_opt_params=amp_opt_params)
optimizer.step()
# compute alignment error (the lower the better )
align_error = 1 - alignment_diagonal_score(alignments)
loss_dict['align_error'] = align_error
# backpass and check the grad norm for stop loss
if c.separate_stopnet:
loss_dict['stopnet_loss'].backward()
optimizer_st, _ = adam_weight_decay(optimizer_st)
if amp:
amp_opt_params = amp.master_params(optimizer)
else:
amp_opt_params = None
grad_norm_st, _ = check_update(model.decoder.stopnet,
1.0,
amp_opt_params=amp_opt_params)
optimizer_st.step()
else:
grad_norm_st = 0
step_time = time.time() - start_time
epoch_time += step_time
# aggregate losses from processes
if num_gpus > 1:
loss_dict['postnet_loss'] = reduce_tensor(
loss_dict['postnet_loss'].data, num_gpus)
loss_dict['decoder_loss'] = reduce_tensor(
loss_dict['decoder_loss'].data, num_gpus)
loss_dict['loss'] = reduce_tensor(loss_dict['loss'].data, num_gpus)
loss_dict['stopnet_loss'] = reduce_tensor(
loss_dict['stopnet_loss'].data,
num_gpus) if c.stopnet else loss_dict['stopnet_loss']
# detach loss values
loss_dict_new = dict()
for key, value in loss_dict.items():
if isinstance(value, (int, float)):
loss_dict_new[key] = value
else:
loss_dict_new[key] = value.item()
loss_dict = loss_dict_new
# update avg stats
update_train_values = dict()
for key, value in loss_dict.items():
update_train_values['avg_' + key] = value
update_train_values['avg_loader_time'] = loader_time
update_train_values['avg_step_time'] = step_time
keep_avg.update_values(update_train_values)
# print training progress
if global_step % c.print_step == 0:
log_dict = {
"avg_spec_length": [avg_spec_length, 1], # value, precision
"avg_text_length": [avg_text_length, 1],
"step_time": [step_time, 4],
"loader_time": [loader_time, 2],
"current_lr": current_lr,
}
c_logger.print_train_step(batch_n_iter, num_iter, global_step,
log_dict, loss_dict, keep_avg.avg_values)
if args.rank == 0:
# Plot Training Iter Stats
# reduce TB load
if global_step % c.tb_plot_step == 0:
iter_stats = {
"lr": current_lr,
"grad_norm": grad_norm,
"grad_norm_st": grad_norm_st,
"step_time": step_time
}
iter_stats.update(loss_dict)
tb_logger.tb_train_iter_stats(global_step, iter_stats)
if global_step % c.save_step == 0:
if c.checkpoint:
# save model
save_checkpoint(
model,
optimizer,
global_step,
epoch,
model.decoder.r,
OUT_PATH,
optimizer_st=optimizer_st,
model_loss=loss_dict['postnet_loss'],
amp_state_dict=amp.state_dict() if amp else None)
# Diagnostic visualizations
const_spec = postnet_output[0].data.cpu().numpy()
gt_spec = linear_input[0].data.cpu().numpy() if c.model in [
"Tacotron", "TacotronGST"
] else mel_input[0].data.cpu().numpy()
align_img = alignments[0].data.cpu().numpy()
figures = {
"prediction":
plot_spectrogram(const_spec, ap, output_fig=False),
"ground_truth":
plot_spectrogram(gt_spec, ap, output_fig=False),
"alignment":
plot_alignment(align_img, output_fig=False),
}
if c.bidirectional_decoder or c.double_decoder_consistency:
figures["alignment_backward"] = plot_alignment(
alignments_backward[0].data.cpu().numpy(),
output_fig=False)
tb_logger.tb_train_figures(global_step, figures)
# Sample audio
if c.model in ["Tacotron", "TacotronGST"]:
train_audio = ap.inv_spectrogram(const_spec.T)
else:
train_audio = ap.inv_melspectrogram(const_spec.T)
tb_logger.tb_train_audios(global_step,
{'TrainAudio': train_audio},
c.audio["sample_rate"])
end_time = time.time()
# print epoch stats
c_logger.print_train_epoch_end(global_step, epoch, epoch_time, keep_avg)
# Plot Epoch Stats
if args.rank == 0:
epoch_stats = {"epoch_time": epoch_time}
epoch_stats.update(keep_avg.avg_values)
tb_logger.tb_train_epoch_stats(global_step, epoch_stats)
if c.tb_model_param_stats:
tb_logger.tb_model_weights(model, global_step)
return keep_avg.avg_values, global_step
def train(data_loader, model, criterion, optimizer, optimizer_st, scheduler,
ap, global_step, epoch, scaler, scaler_st):
model.train()
epoch_time = 0
keep_avg = KeepAverage()
if use_cuda:
batch_n_iter = int(
len(data_loader.dataset) / (c.batch_size * num_gpus))
else:
batch_n_iter = int(len(data_loader.dataset) / c.batch_size)
end_time = time.time()
c_logger.print_train_start()
for num_iter, data in enumerate(data_loader):
start_time = time.time()
# format data
(
text_input,
text_lengths,
mel_input,
mel_lengths,
linear_input,
stop_targets,
speaker_ids,
speaker_embeddings,
max_text_length,
max_spec_length,
) = format_data(data)
loader_time = time.time() - end_time
global_step += 1
# setup lr
if c.noam_schedule:
scheduler.step()
optimizer.zero_grad()
if optimizer_st:
optimizer_st.zero_grad()
with torch.cuda.amp.autocast(enabled=c.mixed_precision):
# forward pass model
if c.bidirectional_decoder or c.double_decoder_consistency:
(
decoder_output,
postnet_output,
alignments,
stop_tokens,
decoder_backward_output,
alignments_backward,
) = model(
text_input,
text_lengths,
mel_input,
mel_lengths,
speaker_ids=speaker_ids,
speaker_embeddings=speaker_embeddings,
)
else:
decoder_output, postnet_output, alignments, stop_tokens = model(
text_input,
text_lengths,
mel_input,
mel_lengths,
speaker_ids=speaker_ids,
speaker_embeddings=speaker_embeddings,
)
decoder_backward_output = None
alignments_backward = None
# set the [alignment] lengths wrt reduction factor for guided attention
if mel_lengths.max() % model.decoder.r != 0:
alignment_lengths = (
mel_lengths +
(model.decoder.r -
(mel_lengths.max() % model.decoder.r))) // model.decoder.r
else:
alignment_lengths = mel_lengths // model.decoder.r
# compute loss
loss_dict = criterion(
postnet_output,
decoder_output,
mel_input,
linear_input,
stop_tokens,
stop_targets,
mel_lengths,
decoder_backward_output,
alignments,
alignment_lengths,
alignments_backward,
text_lengths,
)
# check nan loss
if torch.isnan(loss_dict["loss"]).any():
raise RuntimeError(f"Detected NaN loss at step {global_step}.")
# optimizer step
if c.mixed_precision:
# model optimizer step in mixed precision mode
scaler.scale(loss_dict["loss"]).backward()
scaler.unscale_(optimizer)
optimizer, current_lr = adam_weight_decay(optimizer)
grad_norm, _ = check_update(model,
c.grad_clip,
ignore_stopnet=True)
scaler.step(optimizer)
scaler.update()
# stopnet optimizer step
if c.separate_stopnet:
scaler_st.scale(loss_dict["stopnet_loss"]).backward()
scaler.unscale_(optimizer_st)
optimizer_st, _ = adam_weight_decay(optimizer_st)
grad_norm_st, _ = check_update(model.decoder.stopnet, 1.0)
scaler_st.step(optimizer)
scaler_st.update()
else:
grad_norm_st = 0
else:
# main model optimizer step
loss_dict["loss"].backward()
optimizer, current_lr = adam_weight_decay(optimizer)
grad_norm, _ = check_update(model,
c.grad_clip,
ignore_stopnet=True)
optimizer.step()
# stopnet optimizer step
if c.separate_stopnet:
loss_dict["stopnet_loss"].backward()
optimizer_st, _ = adam_weight_decay(optimizer_st)
grad_norm_st, _ = check_update(model.decoder.stopnet, 1.0)
optimizer_st.step()
else:
grad_norm_st = 0
# compute alignment error (the lower the better )
align_error = 1 - alignment_diagonal_score(alignments)
loss_dict["align_error"] = align_error
step_time = time.time() - start_time
epoch_time += step_time
# aggregate losses from processes
if num_gpus > 1:
loss_dict["postnet_loss"] = reduce_tensor(
loss_dict["postnet_loss"].data, num_gpus)
loss_dict["decoder_loss"] = reduce_tensor(
loss_dict["decoder_loss"].data, num_gpus)
loss_dict["loss"] = reduce_tensor(loss_dict["loss"].data, num_gpus)
loss_dict["stopnet_loss"] = (reduce_tensor(
loss_dict["stopnet_loss"].data, num_gpus) if c.stopnet else
loss_dict["stopnet_loss"])
# detach loss values
loss_dict_new = dict()
for key, value in loss_dict.items():
if isinstance(value, (int, float)):
loss_dict_new[key] = value
else:
loss_dict_new[key] = value.item()
loss_dict = loss_dict_new
# update avg stats
update_train_values = dict()
for key, value in loss_dict.items():
update_train_values["avg_" + key] = value
update_train_values["avg_loader_time"] = loader_time
update_train_values["avg_step_time"] = step_time
keep_avg.update_values(update_train_values)
# print training progress
if global_step % c.print_step == 0:
log_dict = {
"max_spec_length": [max_spec_length, 1], # value, precision
"max_text_length": [max_text_length, 1],
"step_time": [step_time, 4],
"loader_time": [loader_time, 2],
"current_lr": current_lr,
}
c_logger.print_train_step(batch_n_iter, num_iter, global_step,
log_dict, loss_dict, keep_avg.avg_values)
if args.rank == 0:
# Plot Training Iter Stats
# reduce TB load
if global_step % c.tb_plot_step == 0:
iter_stats = {
"lr": current_lr,
"grad_norm": grad_norm,
"grad_norm_st": grad_norm_st,
"step_time": step_time,
}
iter_stats.update(loss_dict)
tb_logger.tb_train_iter_stats(global_step, iter_stats)
if global_step % c.save_step == 0:
if c.checkpoint:
# save model
save_checkpoint(
model,
optimizer,
global_step,
epoch,
model.decoder.r,
OUT_PATH,
optimizer_st=optimizer_st,
model_loss=loss_dict["postnet_loss"],
characters=model_characters,
scaler=scaler.state_dict()
if c.mixed_precision else None,
)
# Diagnostic visualizations
const_spec = postnet_output[0].data.cpu().numpy()
gt_spec = (linear_input[0].data.cpu().numpy() if c.model in [
"Tacotron", "TacotronGST"
] else mel_input[0].data.cpu().numpy())
align_img = alignments[0].data.cpu().numpy()
figures = {
"prediction":
plot_spectrogram(const_spec, ap, output_fig=False),
"ground_truth":
plot_spectrogram(gt_spec, ap, output_fig=False),
"alignment":
plot_alignment(align_img, output_fig=False),
}
if c.bidirectional_decoder or c.double_decoder_consistency:
figures["alignment_backward"] = plot_alignment(
alignments_backward[0].data.cpu().numpy(),
output_fig=False)
tb_logger.tb_train_figures(global_step, figures)
# Sample audio
if c.model in ["Tacotron", "TacotronGST"]:
train_audio = ap.inv_spectrogram(const_spec.T)
else:
train_audio = ap.inv_melspectrogram(const_spec.T)
tb_logger.tb_train_audios(global_step,
{"TrainAudio": train_audio},
c.audio["sample_rate"])
end_time = time.time()
# print epoch stats
c_logger.print_train_epoch_end(global_step, epoch, epoch_time, keep_avg)
# Plot Epoch Stats
if args.rank == 0:
epoch_stats = {"epoch_time": epoch_time}
epoch_stats.update(keep_avg.avg_values)
tb_logger.tb_train_epoch_stats(global_step, epoch_stats)
if c.tb_model_param_stats:
tb_logger.tb_model_weights(model, global_step)
return keep_avg.avg_values, global_step
def train(model, criterion, optimizer, optimizer_st, scheduler, ap,
global_step, epoch):
data_loader = setup_loader(ap,
model.decoder.r,
is_val=False,
verbose=(epoch == 0))
model.train()
epoch_time = 0
train_values = {
'avg_postnet_loss': 0,
'avg_decoder_loss': 0,
'avg_stopnet_loss': 0,
'avg_align_error': 0,
'avg_step_time': 0,
'avg_loader_time': 0
}
if c.bidirectional_decoder:
train_values['avg_decoder_b_loss'] = 0 # decoder backward loss
train_values['avg_decoder_c_loss'] = 0 # decoder consistency loss
if c.ga_alpha > 0:
train_values['avg_ga_loss'] = 0 # guidede attention loss
keep_avg = KeepAverage()
keep_avg.add_values(train_values)
if use_cuda:
batch_n_iter = int(
len(data_loader.dataset) / (c.batch_size * num_gpus))
else:
batch_n_iter = int(len(data_loader.dataset) / c.batch_size)
end_time = time.time()
c_logger.print_train_start()
for num_iter, data in enumerate(data_loader):
start_time = time.time()
# format data
text_input, text_lengths, mel_input, mel_lengths, linear_input, stop_targets, speaker_ids, avg_text_length, avg_spec_length = format_data(
data)
loader_time = time.time() - end_time
global_step += 1
# setup lr
if c.noam_schedule:
scheduler.step()
optimizer.zero_grad()
if optimizer_st:
optimizer_st.zero_grad()
# forward pass model
if c.bidirectional_decoder:
decoder_output, postnet_output, alignments, stop_tokens, decoder_backward_output, alignments_backward = model(
text_input, text_lengths, mel_input, speaker_ids=speaker_ids)
else:
decoder_output, postnet_output, alignments, stop_tokens = model(
text_input, text_lengths, mel_input, speaker_ids=speaker_ids)
decoder_backward_output = None
# set the alignment lengths wrt reduction factor for guided attention
if mel_lengths.max() % model.decoder.r != 0:
alignment_lengths = (
mel_lengths +
(model.decoder.r -
(mel_lengths.max() % model.decoder.r))) // model.decoder.r
else:
alignment_lengths = mel_lengths // model.decoder.r
# compute loss
loss_dict = criterion(postnet_output, decoder_output, mel_input,
linear_input, stop_tokens, stop_targets,
mel_lengths, decoder_backward_output, alignments,
alignment_lengths, text_lengths)
if c.bidirectional_decoder:
keep_avg.update_values({
'avg_decoder_b_loss':
loss_dict['decoder_backward_loss'].item(),
'avg_decoder_c_loss':
loss_dict['decoder_c_loss'].item()
})
if c.ga_alpha > 0:
keep_avg.update_values(
{'avg_ga_loss': loss_dict['ga_loss'].item()})
# backward pass
loss_dict['loss'].backward()
optimizer, current_lr = adam_weight_decay(optimizer)
grad_norm, _ = check_update(model, c.grad_clip, ignore_stopnet=True)
optimizer.step()
# compute alignment error (the lower the better )
align_error = 1 - alignment_diagonal_score(alignments)
keep_avg.update_value('avg_align_error', align_error)
loss_dict['align_error'] = align_error
# backpass and check the grad norm for stop loss
if c.separate_stopnet:
loss_dict['stopnet_loss'].backward()
optimizer_st, _ = adam_weight_decay(optimizer_st)
grad_norm_st, _ = check_update(model.decoder.stopnet, 1.0)
optimizer_st.step()
else:
grad_norm_st = 0
step_time = time.time() - start_time
epoch_time += step_time
# update avg stats
update_train_values = {
'avg_postnet_loss': float(loss_dict['postnet_loss'].item()),
'avg_decoder_loss': float(loss_dict['decoder_loss'].item()),
'avg_stopnet_loss': loss_dict['stopnet_loss'].item() \
if isinstance(loss_dict['stopnet_loss'], float) else float(loss_dict['stopnet_loss'].item()),
'avg_step_time': step_time,
'avg_loader_time': loader_time
}
keep_avg.update_values(update_train_values)
if global_step % c.print_step == 0:
c_logger.print_train_step(batch_n_iter, num_iter, global_step,
avg_spec_length, avg_text_length,
step_time, loader_time, current_lr,
loss_dict, keep_avg.avg_values)
# aggregate losses from processes
if num_gpus > 1:
loss_dict['postnet_loss'] = reduce_tensor(
loss_dict['postnet_loss'].data, num_gpus)
loss_dict['decoder_loss'] = reduce_tensor(
loss_dict['decoder_loss'].data, num_gpus)
loss_dict['loss'] = reduce_tensor(loss_dict['loss'].data, num_gpus)
loss_dict['stopnet_loss'] = reduce_tensor(
loss_dict['stopnet_loss'].data,
num_gpus) if c.stopnet else loss_dict['stopnet_loss']
if args.rank == 0:
# Plot Training Iter Stats
# reduce TB load
if global_step % 10 == 0:
iter_stats = {
"loss_posnet": loss_dict['postnet_loss'].item(),
"loss_decoder": loss_dict['decoder_loss'].item(),
"lr": current_lr,
"grad_norm": grad_norm,
"grad_norm_st": grad_norm_st,
"step_time": step_time
}
tb_logger.tb_train_iter_stats(global_step, iter_stats)
if global_step % c.save_step == 0:
if c.checkpoint:
# save model
save_checkpoint(
model,
optimizer,
global_step,
epoch,
model.decoder.r,
OUT_PATH,
optimizer_st=optimizer_st,
model_loss=loss_dict['postnet_loss'].item())
# Diagnostic visualizations
const_spec = postnet_output[0].data.cpu().numpy()
gt_spec = linear_input[0].data.cpu().numpy() if c.model in [
"Tacotron", "TacotronGST"
] else mel_input[0].data.cpu().numpy()
align_img = alignments[0].data.cpu().numpy()
figures = {
"prediction": plot_spectrogram(const_spec, ap),
"ground_truth": plot_spectrogram(gt_spec, ap),
"alignment": plot_alignment(align_img),
}
if c.bidirectional_decoder:
figures["alignment_backward"] = plot_alignment(
alignments_backward[0].data.cpu().numpy())
tb_logger.tb_train_figures(global_step, figures)
# Sample audio
if c.model in ["Tacotron", "TacotronGST"]:
train_audio = ap.inv_spectrogram(const_spec.T)
else:
train_audio = ap.inv_melspectrogram(const_spec.T)
tb_logger.tb_train_audios(global_step,
{'TrainAudio': train_audio},
c.audio["sample_rate"])
end_time = time.time()
# print epoch stats
c_logger.print_train_epoch_end(global_step, epoch, epoch_time, keep_avg)
# Plot Epoch Stats
if args.rank == 0:
# Plot Training Epoch Stats
epoch_stats = {
"loss_postnet": keep_avg['avg_postnet_loss'],
"loss_decoder": keep_avg['avg_decoder_loss'],
"stopnet_loss": keep_avg['avg_stopnet_loss'],
"alignment_score": keep_avg['avg_align_error'],
"epoch_time": epoch_time
}
if c.ga_alpha > 0:
epoch_stats['guided_attention_loss'] = keep_avg['avg_ga_loss']
tb_logger.tb_train_epoch_stats(global_step, epoch_stats)
if c.tb_model_param_stats:
tb_logger.tb_model_weights(model, global_step)
return keep_avg.avg_values, global_step