def __init__(self, gans_value_function=None, feature_matching=False):
'''
Init.
Args:
gans_value_function: is-a `GANsValueFunction`.
'''
if gans_value_function is None:
gans_value_function = MiniMax()
if feature_matching is False:
feature_matching = FeatureMatching()
if isinstance(gans_value_function, GANsValueFunction) is False:
raise TypeError(
"The type of `gans_value_function` must be `GANsValueFunction`."
)
if isinstance(
feature_matching,
FeatureMatching) is False and feature_matching is not None:
raise TypeError(
"The type of `feature_matching` must be `FeatureMatching`.")
self.__gans_value_function = gans_value_function
self.__feature_matching = feature_matching
self.__logger = getLogger("pygan")
def __init__(self, gans_value_function=None):
'''
Init.
Args:
gans_value_function: is-a `GANsValueFunction`.
'''
if gans_value_function is None:
gans_value_function = MiniMax()
if isinstance(gans_value_function, GANsValueFunction) is False:
raise TypeError("The type of `gans_value_function` must be `GANsValueFunction`.")
self.__gans_value_function = gans_value_function
self.__logger = getLogger("pygan")
def __init__(self,
midi_path_list,
batch_size=20,
seq_len=8,
time_fraction=1.0,
learning_rate=1e-10,
hidden_dim=15200,
generative_model=None,
discriminative_model=None,
gans_value_function=None):
'''
Init.
Args:
midi_path_list: `list` of paths to MIDI files.
batch_size: Batch size.
seq_len: The length of sequence that LSTM networks will observe.
time_fraction: Time fraction or time resolution (seconds).
learning_rate: Learning rate in `Generator` and `Discriminator`.
hidden_dim: The number of units in hidden layer of `DiscriminativeModel`.
true_sampler: is-a `TrueSampler`.
noise_sampler: is-a `NoiseSampler`.
generative_model: is-a `GenerativeModel`.
discriminative_model: is-a `DiscriminativeModel`.
gans_value_function: is-a `GANsValueFunction`.
'''
self.__midi_controller = MidiController()
self.__midi_df_list = [
self.__midi_controller.extract(midi_path)
for midi_path in midi_path_list
]
bar_gram = BarGram(midi_df_list=self.__midi_df_list,
time_fraction=time_fraction)
self.__bar_gram = bar_gram
dim = self.__bar_gram.dim
true_sampler = BarGramTrueSampler(bar_gram=bar_gram,
midi_df_list=self.__midi_df_list,
batch_size=batch_size,
seq_len=seq_len,
time_fraction=time_fraction)
noise_sampler = BarGramNoiseSampler(bar_gram=bar_gram,
midi_df_list=self.__midi_df_list,
batch_size=batch_size,
seq_len=seq_len,
time_fraction=time_fraction)
if generative_model is None:
conv_activation_function = TanhFunction()
conv_activation_function.batch_norm = BatchNorm()
channel = noise_sampler.channel
convolution_layer_list = [
ConvolutionLayer1(
ConvGraph1(activation_function=conv_activation_function,
filter_num=batch_size,
channel=channel,
kernel_size=3,
scale=0.01,
stride=1,
pad=1))
]
deconv_activation_function = SoftmaxFunction()
deconvolution_layer_list = [
DeconvolutionLayer(
DeCNNGraph(activation_function=deconv_activation_function,
filter_num=batch_size,
channel=channel,
kernel_size=3,
scale=0.01,
stride=1,
pad=1))
]
opt_params_deconv = Adam()
deconvolution_model = DeconvolutionModel(
deconvolution_layer_list=deconvolution_layer_list,
opt_params=opt_params_deconv)
opt_params = Adam()
opt_params.dropout_rate = 0.0
generative_model = Generator(
batch_size=batch_size,
layerable_cnn_list=convolution_layer_list,
deconvolution_model=deconvolution_model,
condition_noise_sampler=UniformNoiseSampler(
low=-0.1,
high=0.1,
output_shape=(batch_size, channel, seq_len, dim)),
learning_rate=learning_rate,
)
generative_model.noise_sampler = noise_sampler
if discriminative_model is None:
activation_function = LogisticFunction()
activation_function.batch_norm = BatchNorm()
# First convolution layer.
conv2 = ConvolutionLayer2(
# Computation graph for first convolution layer.
ConvGraph2(
# Logistic function as activation function.
activation_function=activation_function,
# The number of `filter`.
filter_num=batch_size,
# The number of channel.
channel=noise_sampler.channel * 2,
# The size of kernel.
kernel_size=3,
# The filter scale.
scale=0.001,
# The nubmer of stride.
stride=1,
# The number of zero-padding.
pad=1))
# Stack.
layerable_cnn_list = [conv2]
opt_params = Adam()
opt_params.dropout_rate = 0.0
if hidden_dim is None:
hidden_dim = channel * seq_len * dim
cnn_output_activating_function = LogisticFunction()
cnn_output_graph = CNNOutputGraph(
hidden_dim=hidden_dim,
output_dim=1,
activating_function=cnn_output_activating_function,
scale=0.01)
discriminative_model = Discriminator(
batch_size=batch_size,
layerable_cnn_list=layerable_cnn_list,
cnn_output_graph=cnn_output_graph,
opt_params=opt_params,
computable_loss=CrossEntropy(),
learning_rate=learning_rate)
if gans_value_function is None:
gans_value_function = MiniMax()
GAN = GenerativeAdversarialNetworks(
gans_value_function=gans_value_function,
feature_matching=FeatureMatching(lambda1=0.01, lambda2=0.99))
self.__noise_sampler = noise_sampler
self.__true_sampler = true_sampler
self.__generative_model = generative_model
self.__discriminative_model = discriminative_model
self.__GAN = GAN
self.__time_fraction = time_fraction
def __init__(self,
midi_path_list,
target_program=0,
batch_size=10,
seq_len=4,
time_fraction=1.0,
true_sampler=None,
noise_sampler=None,
generative_model=None,
discriminative_model=None,
gans_value_function=None):
'''
Init.
Args:
midi_path_list: `list` of paths to MIDI files.
target_program: Program in generated MIDI.
batch_size: Batch size.
seq_len: The length of sequence that LSTM networks will observe.
time_fraction: Time fraction or time resolution (seconds).
true_sampler: is-a `TrueSampler`.
noise_sampler: is-a `NoiseSampler`.
generative_model: is-a `GenerativeModel`.
discriminative_model: is-a `DiscriminativeModel`.
gans_value_function: is-a `GANsValueFunction`.
'''
self.__midi_controller = MidiController()
self.__midi_df_list = [
self.__midi_controller.extract(midi_path)
for midi_path in midi_path_list
]
# The dimension of observed or feature points.
dim = 12
if true_sampler is None:
true_sampler = MidiTrueSampler(midi_path_list=midi_path_list,
batch_size=batch_size,
seq_len=seq_len)
if noise_sampler is None:
noise_sampler = MidiNoiseSampler(batch_size=batch_size)
if generative_model is None:
hidden_activating_function = TanhFunction()
hidden_activating_function.batch_norm = BatchNorm()
generative_model = Generator(
batch_size=batch_size,
seq_len=seq_len,
input_neuron_count=dim,
hidden_neuron_count=dim,
hidden_activating_function=hidden_activating_function)
generative_model.noise_sampler = noise_sampler
if discriminative_model is None:
discriminative_model = Discriminator(batch_size=batch_size,
seq_len=seq_len,
input_neuron_count=dim,
hidden_neuron_count=dim)
if gans_value_function is None:
gans_value_function = MiniMax()
GAN = GenerativeAdversarialNetworks(
gans_value_function=gans_value_function)
self.__true_sampler = true_sampler
self.__generative_model = generative_model
self.__discriminative_model = discriminative_model
self.__GAN = GAN
self.__time_fraction = time_fraction
self.__target_program = target_program