You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
hello , thanks alot for this awesome work , i installed the repo on my wsl2 ubuntu 22.04 and installed the packages using conda i also used gpu so i checked comments and was able to use gpu but the issue is that when i reach the training i get this error
2023-11-30 13:41:31.626134: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2023-11-30 13:41:31.626214: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2023-11-30 13:41:31.627161: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2023-11-30 13:41:32.676863: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/tensorflow_addons/utils/tfa_eol_msg.py:23: UserWarning:
TensorFlow Addons (TFA) has ended development and introduction of new features.
TFA has entered a minimal maintenance and release mode until a planned end of life in May 2024.
Please modify downstream libraries to take dependencies from other repositories in our TensorFlow community (e.g. Keras, Keras-CV, and Keras-NLP).
For more information see: https://github.com/tensorflow/addons/issues/2807
warnings.warn(
I1130 13:41:37.002290 139773808506688 ddsp_run.py:180] Restore Dir: /home/genesis/github/ddsp/ddsp-solo-instrument
I1130 13:41:37.002723 139773808506688 ddsp_run.py:181] Save Dir: /home/genesis/github/ddsp/ddsp-solo-instrument
I1130 13:41:37.037069 139773808506688 ddsp_run.py:153] Operative config not found in /home/genesis/github/ddsp/ddsp-solo-instrument
I1130 13:41:37.056087 139773808506688 ddsp_run.py:185] Operative Gin Config:
import ddsp
import ddsp.training as ddsp2
# Macros:
# ==============================================================================
batch_size = 1
evaluators = [@BasicEvaluator]
learning_rate = 0.0003
# Parameters for Add:
# ==============================================================================
Add.name = 'add'
# Parameters for Autoencoder:
# ==============================================================================
Autoencoder.decoder = @decoders.RnnFcDecoder()
Autoencoder.encoder = None
Autoencoder.losses = [@losses.SpectralLoss()]
Autoencoder.preprocessor = @preprocessing.F0LoudnessPreprocessor()
Autoencoder.processor_group = @processors.ProcessorGroup()
# Parameters for evaluate:
# ==============================================================================
evaluate.batch_size = 32
evaluate.data_provider = @data.TFRecordProvider()
evaluate.evaluator_classes = %evaluators
evaluate.num_batches = 5
# Parameters for F0LoudnessPreprocessor:
# ==============================================================================
F0LoudnessPreprocessor.time_steps = 1000
# Parameters for FilteredNoise:
# ==============================================================================
FilteredNoise.n_samples = 64000
FilteredNoise.name = 'filtered_noise'
FilteredNoise.scale_fn = @core.exp_sigmoid
FilteredNoise.window_size = 0
# Parameters for get_model:
# ==============================================================================
get_model.model = @models.Autoencoder()
# Parameters for Harmonic:
# ==============================================================================
Harmonic.n_samples = 64000
Harmonic.name = 'harmonic'
Harmonic.normalize_below_nyquist = True
Harmonic.sample_rate = 16000
Harmonic.scale_fn = @core.exp_sigmoid
# Parameters for MfccTimeDistributedRnnEncoder:
# ==============================================================================
MfccTimeDistributedRnnEncoder.rnn_channels = 512
MfccTimeDistributedRnnEncoder.rnn_type = 'gru'
MfccTimeDistributedRnnEncoder.z_dims = 16
MfccTimeDistributedRnnEncoder.z_time_steps = 125
# Parameters for ProcessorGroup:
# ==============================================================================
ProcessorGroup.dag = \
[(@synths.Harmonic(), ['amps', 'harmonic_distribution', 'f0_hz']),
(@synths.FilteredNoise(), ['noise_magnitudes']),
(@processors.Add(), ['filtered_noise/signal', 'harmonic/signal']),
(@effects.Reverb(), ['add/signal'])]
# Parameters for Reverb:
# ==============================================================================
Reverb.name = 'reverb'
Reverb.reverb_length = 48000
Reverb.trainable = True
# Parameters for RnnFcDecoder:
# ==============================================================================
RnnFcDecoder.ch = 512
RnnFcDecoder.input_keys = ('ld_scaled', 'f0_scaled')
RnnFcDecoder.layers_per_stack = 3
RnnFcDecoder.output_splits = \
(('amps', 1), ('harmonic_distribution', 60), ('noise_magnitudes', 65))
RnnFcDecoder.rnn_channels = 512
RnnFcDecoder.rnn_type = 'gru'
# Parameters for sample:
# ==============================================================================
sample.batch_size = 16
sample.ckpt_delay_secs = 300
sample.data_provider = @data.TFRecordProvider()
sample.evaluator_classes = %evaluators
sample.num_batches = 1
# Parameters for SpectralLoss:
# ==============================================================================
SpectralLoss.logmag_weight = 1.0
SpectralLoss.loss_type = 'L1'
SpectralLoss.mag_weight = 1.0
# Parameters for TFRecordProvider:
# ==============================================================================
TFRecordProvider.file_pattern = \
'/home/genesis/github/ddsp/dataset/train.tfrecord-*'
# Parameters for train:
# ==============================================================================
train.batch_size = %batch_size
train.data_provider = @data.TFRecordProvider()
train.num_steps = 30000
train.steps_per_save = 300
train.steps_per_summary = 300
# Parameters for Trainer:
# ==============================================================================
Trainer.checkpoints_to_keep = 10
Trainer.grad_clip_norm = 3.0
Trainer.learning_rate = %learning_rate
Trainer.lr_decay_rate = 0.98
Trainer.lr_decay_steps = 10000
I1130 13:41:37.197552 139773808506688 train_util.py:78] Defaulting to MirroredStrategy
INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:GPU:0',)
I1130 13:41:39.469777 139773808506688 mirrored_strategy.py:423] Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:GPU:0',)
I1130 13:41:41.570941 139773808506688 trainers.py:142] Building the model...
Model: "autoencoder"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
f0_loudness_preprocessor ( multiple 0
F0LoudnessPreprocessor)
rnn_fc_decoder (RnnFcDecod multiple 4801150
er)
processor_group (Processor multiple 48000
Group)
spectral_loss (SpectralLos multiple 0
s)
=================================================================
Total params: 4849150 (18.50 MB)
Trainable params: 4849150 (18.50 MB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________
I1130 13:42:00.145416 139773808506688 trainers.py:95] Restoring from checkpoint...
I1130 13:42:00.145583 139773808506688 trainers.py:103] Trainer restoring the full model
I1130 13:42:00.146856 139773808506688 train_util.py:267] No existing checkpoint found in /home/genesis/github/ddsp/ddsp-solo-instrument, skipping checkpoint loading.
Traceback (most recent call last):
File "/home/genesis/miniconda3/envs/ddsp/bin/ddsp_run", line 8, in <module>
sys.exit(console_entry_point())
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/ddsp/training/ddsp_run.py", line 229, in console_entry_point
app.run(main)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/absl/app.py", line 308, in run
_run_main(main, args)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/absl/app.py", line 254, in _run_main
sys.exit(main(argv))
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/ddsp/training/ddsp_run.py", line 199, in main
train_util.train(data_provider=gin.REQUIRED,
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/gin/config.py", line 1605, in gin_wrapper
utils.augment_exception_message_and_reraise(e, err_str)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/gin/utils.py", line 41, in augment_exception_message_and_reraise
raise proxy.with_traceback(exception.__traceback__) from None
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/gin/config.py", line 1582, in gin_wrapper
return fn(*new_args, **new_kwargs)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/ddsp/training/train_util.py", line 289, in train
losses = trainer.train_step(dataset_iter)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/tensorflow/python/util/traceback_utils.py", line 153, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/tmp/__autograph_generated_fileg0vv7gcp.py", line 12, in tf__train_step
losses = ag__.converted_call(ag__.ld(self).run, (ag__.ld(self).step_fn, ag__.ld(batch)), None, fscope)
File "/tmp/__autograph_generated_file3in1ge92.py", line 13, in tf__run
retval_ = ag__.converted_call(ag__.ld(self).strategy.run, (ag__.ld(fn),), dict(args=ag__.ld(args), kwargs=ag__.ld(kwargs)), fscope)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/tensorflow/core/function/trace_type/trace_type_builder.py", line 144, in from_value
elif isinstance(value, trace.SupportsTracingProtocol):
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/typing_extensions.py", line 689, in __instancecheck__
val = inspect.getattr_static(instance, attr)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/inspect.py", line 1743, in getattr_static
instance_result = _check_instance(obj, attr)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/inspect.py", line 1690, in _check_instance
instance_dict = object.__getattribute__(obj, "__dict__")
TypeError: in user code:
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/ddsp/training/trainers.py", line 158, in train_step *
losses = self.run(self.step_fn, batch)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/ddsp/training/trainers.py", line 138, in run *
return self.strategy.run(fn, args=args, kwargs=kwargs)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/tensorflow/core/function/trace_type/trace_type_builder.py", line 144, in from_value
elif isinstance(value, trace.SupportsTracingProtocol):
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/site-packages/typing_extensions.py", line 689, in __instancecheck__
val = inspect.getattr_static(instance, attr)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/inspect.py", line 1743, in getattr_static
instance_result = _check_instance(obj, attr)
File "/home/genesis/miniconda3/envs/ddsp/lib/python3.10/inspect.py", line 1690, in _check_instance
instance_dict = object.__getattribute__(obj, "__dict__")
TypeError: this __dict__ descriptor does not support '_DictWrapper' objects
In call to configurable 'train' (<function train at 0x7f1f2971a050>)
hello , thanks alot for this awesome work , i installed the repo on my wsl2 ubuntu 22.04 and installed the packages using conda i also used gpu so i checked comments and was able to use gpu but the issue is that when i reach the training i get this error
here is the env i used python 3.10 :
name: ddsp
channels:
dependencies:
prefix: /home/genesis/miniconda3/envs/ddsp
The text was updated successfully, but these errors were encountered: