yqzhishen
commented
3 months ago You are not using our repository directly. Please raise your issue to the repository you are using.
Closed c7e715d1b04b17683718fb1e8944cc28 closed 3 months ago
yqzhishen
commented
3 months ago You are not using our repository directly. Please raise your issue to the repository you are using.
c7e715d1b04b17683718fb1e8944cc28
commented
3 months ago Sorry, but this error also occurs when using the DiffSinger repository directly.
Traceback (most recent call last):
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\scripts\train.py", line 31, in <module>
run_task()
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\scripts\train.py", line 27, in run_task
task_cls.start()
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\basics\base_task.py", line 467, in start
trainer.fit(task, ckpt_path=get_latest_checkpoint_path(work_dir))
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\trainer\trainer.py", line 544, in fit
call._call_and_handle_interrupt(
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\trainer\call.py", line 44, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\trainer\trainer.py", line 580, in _fit_impl
self._run(model, ckpt_path=ckpt_path)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\trainer\trainer.py", line 989, in _run
results = self._run_stage()
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\trainer\trainer.py", line 1035, in _run_stage
self.fit_loop.run()
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\fit_loop.py", line 202, in run
self.advance()
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\fit_loop.py", line 359, in advance
self.epoch_loop.run(self._data_fetcher)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\training_epoch_loop.py", line 136, in run
self.advance(data_fetcher)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\training_epoch_loop.py", line 240, in advance
batch_output = self.automatic_optimization.run(trainer.optimizers[0], batch_idx, kwargs)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\optimization\automatic.py", line 187, in run
self._optimizer_step(batch_idx, closure)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\optimization\automatic.py", line 265, in _optimizer_step
call._call_lightning_module_hook(
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\trainer\call.py", line 157, in _call_lightning_module_hook
output = fn(*args, **kwargs)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\core\module.py", line 1291, in optimizer_step
optimizer.step(closure=optimizer_closure)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\core\optimizer.py", line 151, in step
step_output = self._strategy.optimizer_step(self._optimizer, closure, **kwargs)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\strategies\strategy.py", line 230, in optimizer_step
return self.precision_plugin.optimizer_step(optimizer, model=model, closure=closure, **kwargs)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\plugins\precision\amp.py", line 77, in optimizer_step
closure_result = closure()
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\optimization\automatic.py", line 140, in __call__
self._result = self.closure(*args, **kwargs)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\optimization\automatic.py", line 126, in closure
step_output = self._step_fn()
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\optimization\automatic.py", line 318, in _training_step
return self.output_result_cls.from_training_step_output(training_step_output, trainer.accumulate_grad_batches)
File "D:\Users\ikki1\Desktop\Projects\DiffSinger\.venv\lib\site-packages\lightning\pytorch\loops\optimization\automatic.py", line 72, in from_training_step_output
raise MisconfigurationException(
lightning.fabric.utilities.exceptions.MisconfigurationException: In automatic optimization, `training_step` must return a Tensor, a dict, or None (where the step will be skipped).Can you upload your config file?
c7e715d1b04b17683718fb1e8944cc28
commented
3 months ago Okay. from the DiffSinger curriculum. https://openvpi-docs.feishu.cn/wiki/Mt13w6wUaiI0zUkN2wkcwyWBndh
base_config: configs/variance.yaml
raw_data_dir:
- data/20240617225409/raw
speakers:
- "20240617225409"
spk_ids: []
test_prefixes:
- _ああいあうえあ_N_A#2
- _ああいあうえあ_N_A#2
- _ああいあうえあ_N_A3
- _ああいあうえあ_N_B2
- _ああいあうえあ_N_C#3
dictionary: dictionaries/jpn_dict.txt
binary_data_dir: data/20240617225409/binary
binarization_args:
num_workers: 0
use_spk_id: false
num_spk: 1
predict_dur: false
predict_pitch: false
predict_energy: false
predict_breathiness: false
predict_voicing: false
predict_tension: false
energy_db_min: -96.0
energy_db_max: -12.0
breathiness_db_min: -96.0
breathiness_db_max: -20.0
voicing_db_min: -96.0
voicing_db_max: -12.0
tension_logit_min: -10.0
tension_logit_max: 10.0
hidden_size: 256
dur_prediction_args:
arch: fs2
hidden_size: 512
dropout: 0.1
num_layers: 5
kernel_size: 3
log_offset: 1.0
loss_type: mse
lambda_pdur_loss: 0.3
lambda_wdur_loss: 1.0
lambda_sdur_loss: 3.0
use_melody_encoder: false
melody_encoder_args:
hidden_size: 128
enc_layers: 4
use_glide_embed: false
glide_types: [up, down]
glide_embed_scale: 11.313708498984760
pitch_prediction_args:
pitd_norm_min: -8.0
pitd_norm_max: 8.0
pitd_clip_min: -12.0
pitd_clip_max: 12.0
repeat_bins: 64
residual_layers: 20
residual_channels: 256
dilation_cycle_length: 5 # *
variances_prediction_args:
total_repeat_bins: 48
residual_layers: 10
residual_channels: 192
dilation_cycle_length: 4 # *
lambda_dur_loss: 1.0
lambda_pitch_loss: 1.0
lambda_var_loss: 1.0
optimizer_args:
lr: 0.0006
lr_scheduler_args:
scheduler_cls: torch.optim.lr_scheduler.StepLR
step_size: 10000
gamma: 0.75
max_batch_frames: 80000
max_batch_size: 9
max_updates: 160000
num_valid_plots: 10
val_check_interval: 2000
num_ckpt_keep: 5
permanent_ckpt_start: 80000
permanent_ckpt_interval: 10000
pl_trainer_devices: 'auto'
pl_trainer_precision: '16-mixed' Please at least turn on one predict_* switch. Otherwise the model has nothing to train.
c7e715d1b04b17683718fb1e8944cc28
commented
3 months ago Thank you! You've been very helpful. We apologize for the inconvenience.
sp1cae
commented
1 month ago Please at least turn on one
predict_*switch. Otherwise the model has nothing to train.
你的意思是 predict_dur: false predict_pitch: false 这两个至少要打开一个吗 我的是这样 predict_dur: false predict_pitch: false predict_energy: ture predict_breathiness: ture predict_voicing: ture predict_tension: false 报错了
In the "base_task.py" file in the "basics" folder, in the "training_step" function in the "BaseTask" class, the "total_loss" variable contains an int of 0.