Я делаю нейронную сеть для прогнозирования аудиоданных (чтобы узнать больше о том, как работают нейронные сети и как использовать тензорный поток), и пока все идет довольно гладко, за одним исключением. Я немного осмотрелся, чтобы решить эту проблему, и не смог найти ничего конкретного, c достаточно, чтобы мне помочь. Я настроил набор данных и модель, и они работают нормально, но по какой-то причине, когда я пытаюсь обучить модель, это дает мне ошибку типа, хотя все значения в наборе данных являются 32-битными числами с плавающей запятой. Было бы очень признательно, если бы кто-нибудь мог ответить на этот вопрос за меня или хотя бы pu sh в правильном направлении, чтобы выяснить это. Код и выходы консоли приведены ниже. (Кстати, все значения в наборе данных находятся между 0 и 1, я не знаю, актуально ли это, но я подумал, что добавлю это)
EDIT: я также включил класс AudioHandler, который вы можно использовать для воспроизведения ошибки. get_audio_array или get_audio_arrays могут использоваться для преобразования отдельного mp3 или каталога mp3 в массив (ы) аудиоданных. Вы также можете использовать dataset_from_arrays для создания набора данных из звуковых массивов, созданных с помощью dataset_from_arrays.
from AudioHandler import AudioHandler
import os
seq_length = 22050
BATCH_SIZE = 64
BUFFER_SIZE = 10000
audio_arrays = AudioHandler.get_audio_arrays("AudioDataset", normalized=True)
dataset = AudioHandler.dataset_from_arrays(audio_arrays, seq_length, BATCH_SIZE, buffer_size=BUFFER_SIZE)
print(dataset)
rnn_units = 256
def build_model(rnn_units, batch_size):
model = tf.keras.Sequential([
tf.keras.layers.InputLayer(batch_input_shape=(batch_size, None, 2)),
tf.keras.layers.GRU(rnn_units, return_sequences=True, stateful=True),
tf.keras.layers.Dense(2)
])
return model
model = build_model(rnn_units, BATCH_SIZE)
model.summary()
model.compile(optimizer='adam', loss=tf.keras.losses.MeanSquaredError)
EPOCHS = 10
history = model.fit(dataset, epochs=EPOCHS)
from pydub import AudioSegment
import numpy as np
from pathlib import Path
from tensorflow import data
import os
class AudioHandler:
@staticmethod
def print_audio_info(file_name):
audio_segment = AudioSegment.from_file(file_name)
print("Information of '" + file_name + "':")
print("Sample rate: " + str(audio_segment.frame_rate) + "kHz")
# Multiply frame_width by 8 to get bits, since it is given in bytes
print("Sample width: " + str(audio_segment.frame_width * 8) + " bits per sample (" + str(
int(audio_segment.frame_width * 8 / audio_segment.channels)) + " bits per channel)")
print("Channels: " + str(audio_segment.channels))
@staticmethod
def get_audio_array(file_name, normalized=True):
audio_segment = AudioSegment.from_file(file_name)
# Get bytestring of raw audio data
raw_audio_bytestring = audio_segment.raw_data
# Adjust sample width to accommodate multiple channels in each sample
sample_width = audio_segment.frame_width / audio_segment.channels
# Convert bytestring to numpy array
if sample_width == 1:
raw_audio = np.array(np.frombuffer(raw_audio_bytestring, dtype=np.int8))
elif sample_width == 2:
raw_audio = np.array(np.frombuffer(raw_audio_bytestring, dtype=np.int16))
elif sample_width == 4:
raw_audio = np.array(np.frombuffer(raw_audio_bytestring, dtype=np.int32))
else:
raw_audio = np.array(np.frombuffer(raw_audio_bytestring, dtype=np.int16))
# Normalize the audio data
if normalized:
# Cast the audio data as 32 bit floats
raw_audio = raw_audio.astype(dtype=np.float32)
# Make all values positive
raw_audio += np.power(2, 8*sample_width)/2
# Normalize all values between 0 and 1
raw_audio *= 1/np.power(2, 8*sample_width)
# Reshape the array to accommodate multiple channels
if audio_segment.channels > 1:
raw_audio = raw_audio.reshape((-1, audio_segment.channels))
return raw_audio
@staticmethod
# Return an array of all audio files in directory, as arrays of audio data
def get_audio_arrays(directory, filetype='mp3', normalized=True):
file_count_total = len([name for name in os.listdir(directory) if os.path.isfile(os.path.join(directory, name))]) - 1
audio_arrays = []
# Iterate through all audio files
pathlist = Path(directory).glob('**/*.' + filetype)
# Keep track of progress
file_count = 0
print("Loading audio files... 0%")
for path in pathlist:
path_string = str(path)
audio_array = AudioHandler.get_audio_array(path_string, normalized=normalized)
audio_arrays.append(audio_array)
# Update Progress
file_count += 1
print('Loading audio files... ' + str(int(file_count/file_count_total*100)) + '%')
return audio_arrays
@staticmethod
def export_to_file(audio_data_array, file_name, normalized=True, file_type="mp3", bitrate="256k"):
if normalized:
audio_data_array *= np.power(2, 16)
audio_data_array -= np.power(2, 16)/2
audio_data_array = audio_data_array.astype(np.int16)
audio_data_array = audio_data_array.reshape((1, -1))[0]
raw_audio = audio_data_array.tostring()
audio_segment = AudioSegment(data=raw_audio, sample_width=2, frame_rate=44100, channels=2)
audio_segment.export(file_name, format=file_type, bitrate=bitrate)
# Splits a sequence into input values and target values
@staticmethod
def __split_input_target(chunk):
input_audio = chunk[:-1]
target_audio = chunk[1:]
return input_audio, target_audio
@staticmethod
def dataset_from_arrays(audio_arrays, sequence_length, batch_size, buffer_size=10000):
# Create main data set, starting with first audio array
dataset = data.Dataset.from_tensor_slices(audio_arrays[0])
dataset = dataset.batch(sequence_length + 1, drop_remainder=True)
# Split each audio array into sequences individually,
# then concatenate each individual data set with the main data set
for i in range(1, len(audio_arrays)):
audio_data = audio_arrays[i]
tensor_slices = data.Dataset.from_tensor_slices(audio_data)
audio_dataset = tensor_slices.batch(sequence_length + 1, drop_remainder=True)
dataset.concatenate(audio_dataset)
dataset = dataset.map(AudioHandler.__split_input_target)
dataset = dataset.shuffle(buffer_size).batch(batch_size, drop_remainder=True)
return dataset
Loading audio files... 0%
Loading audio files... 25%
Loading audio files... 50%
Loading audio files... 75%
Loading audio files... 100%
2020-06-21 00:20:10.796993: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-06-21 00:20:10.811357: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fddb7b23fd0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-06-21 00:20:10.811368: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
<BatchDataset shapes: ((64, 22050, 2), (64, 22050, 2)), types: (tf.float32, tf.float32)>
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
gru (GRU) (64, None, 256) 199680
_________________________________________________________________
dense (Dense) (64, None, 2) 514
=================================================================
Total params: 200,194
Trainable params: 200,194
Non-trainable params: 0
_________________________________________________________________
Epoch 1/10
Traceback (most recent call last):
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/RNN.py", line 57, in <module>
history = model.fit(dataset, epochs=EPOCHS)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 66, in _method_wrapper
return method(self, *args, **kwargs)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 848, in fit
tmp_logs = train_function(iterator)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py", line 580, in __call__
result = self._call(*args, **kwds)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py", line 627, in _call
self._initialize(args, kwds, add_initializers_to=initializers)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py", line 506, in _initialize
*args, **kwds))
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 2446, in _get_concrete_function_internal_garbage_collected
graph_function, _, _ = self._maybe_define_function(args, kwargs)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 2777, in _maybe_define_function
graph_function = self._create_graph_function(args, kwargs)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 2667, in _create_graph_function
capture_by_value=self._capture_by_value),
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py", line 981, in func_graph_from_py_func
func_outputs = python_func(*func_args, **func_kwargs)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py", line 441, in wrapped_fn
return weak_wrapped_fn().__wrapped__(*args, **kwds)
File "/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/framework/func_graph.py", line 968, in wrapper
raise e.ag_error_metadata.to_exception(e)
TypeError: in user code:
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:571 train_function *
outputs = self.distribute_strategy.run(
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:951 run **
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:2290 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/distribute/distribute_lib.py:2649 _call_for_each_replica
return fn(*args, **kwargs)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py:533 train_step **
y, y_pred, sample_weight, regularization_losses=self.losses)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/engine/compile_utils.py:205 __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/losses.py:143 __call__
losses = self.call(y_true, y_pred)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/losses.py:246 call
return self.fn(y_true, y_pred, **self._fn_kwargs)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/losses.py:313 __init__
mean_squared_error, name=name, reduction=reduction)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/losses.py:229 __init__
super(LossFunctionWrapper, self).__init__(reduction=reduction, name=name)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/keras/losses.py:94 __init__
losses_utils.ReductionV2.validate(reduction)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/ops/losses/loss_reduction.py:67 validate
if key not in cls.all():
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/ops/math_ops.py:1491 tensor_equals
return gen_math_ops.equal(self, other, incompatible_shape_error=False)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py:3224 equal
name=name)
/Users/anonteau/Desktop/Development/Python/Lo-FiGenerator/venv/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py:479 _apply_op_helper
repr(values), type(values).__name__, err))
TypeError: Expected float32 passed to parameter 'y' of op 'Equal', got 'auto' of type 'str' instead. Error: Expected float32, got 'auto' of type 'str' instead.```