def __init__(self, config, useTPU=False):
self.config = config
self.useTPU = useTPU
self.num_stacks = self.config['model']['num_stacks']
if type(self.config['model']['dilations']) is int:
self.dilations = [
2**i for i in range(0, self.config['model']['dilations'] + 1)
]
elif type(self.config['model']['dilations']) is list:
self.dilations = self.config['model']['dilations']
self.receptive_field_length = util.compute_receptive_field_length(
config['model']['num_stacks'], self.dilations,
config['model']['filters']['lengths']['res'], 1)
self.target_field_length = config['model']['target_field_length']
self.input_length = self.receptive_field_length + (
self.target_field_length - 1)
self.target_padding = config['model']['target_padding']
self.padded_target_field_length = self.target_field_length + 2 * self.target_padding
self.half_target_field_length = int(self.target_field_length / 2)
self.half_receptive_field_length = int(self.receptive_field_length / 2)
self.num_residual_blocks = len(self.dilations) * self.num_stacks
self.samples_of_interest_indices = self.get_padded_target_field_indices(
)
self.target_sample_indices = self.get_target_field_indices()
self.num_sources = config['model']['num_sources']
self.num_channels = 2
self.epoch_num = 0
self.model = self.setup_model()
def __init__(self, config, load_checkpoint=None, input_length=None, target_field_length=None, print_model_summary=False):
self.config = config
self.verbosity = config['training']['verbosity']
self.num_stacks = self.config['model']['num_stacks']
if type(self.config['model']['dilations']) is int:
self.dilations = [2 ** i for i in range(0, self.config['model']['dilations'] + 1)]
elif type(self.config['model']['dilations']) is list:
self.dilations = self.config['model']['dilations']
self.num_condition_classes = config['dataset']['num_condition_classes']
self.condition_input_length = self.get_condition_input_length(self.config['model']['condition_encoding'])
self.receptive_field_length = int(util.compute_receptive_field_length(config['model']['num_stacks'], self.dilations,
config['model']['filters']['lengths']['res'],
1))
if input_length is not None:
self.input_length = input_length
self.target_field_length = self.input_length - (self.receptive_field_length - 1)
if target_field_length is not None:
self.target_field_length = target_field_length
self.input_length = self.receptive_field_length + (self.target_field_length - 1)
else:
self.target_field_length = config['model']['target_field_length']
self.input_length = self.receptive_field_length + (self.target_field_length - 1)
self.target_padding = config['model']['target_padding']
self.padded_target_field_length = self.target_field_length + 2 * self.target_padding
self.half_target_field_length = self.target_field_length / 2
self.half_receptive_field_length = self.receptive_field_length / 2
self.num_residual_blocks = len(self.dilations) * self.num_stacks
self.activation = keras.layers.Activation('relu')
self.samples_of_interest_indices = self.get_padded_target_field_indices()
self.target_sample_indices = self.get_target_field_indices()
self.optimizer = self.get_optimizer()
self.out_1_loss = self.get_out_1_loss()
self.out_2_loss = self.get_out_2_loss()
self.metrics = self.get_metrics()
self.epoch_num = 0
self.checkpoints_path = ''
self.samples_path = ''
self.history_filename = ''
self.config['model']['num_residual_blocks'] = self.num_residual_blocks
self.config['model']['receptive_field_length'] = self.receptive_field_length
self.config['model']['input_length'] = self.input_length
self.config['model']['target_field_length'] = self.target_field_length
self.model = self.setup_model(load_checkpoint, print_model_summary)
def __init__(self,
config,
load_checkpoint=None,
input_length=None,
target_field_length=None,
print_model_summary=False):
self.config = config
self.verbosity = config['training']['verbosity']
self.num_stacks = self.config['model']['num_stacks']
if type(self.config['model']['dilations']) is int:
self.dilations = [
2**i for i in range(0, self.config['model']['dilations'] + 1)
]
elif type(self.config['model']['dilations']) is list:
self.dilations = self.config['model']['dilations']
self.num_condition_classes = config['dataset']['num_condition_classes']
# not really sure about this one
# it's just ceiling of np.log2(29) where 29 is num cond classes
self.condition_input_length = self.get_condition_input_length(
self.config['model']['condition_encoding'])
# here it is calculating basically the length of all nodes from these dilated stacks?
self.receptive_field_length = util.compute_receptive_field_length(
config['model']['num_stacks'], self.dilations,
config['model']['filters']['lengths']['res'], 1)
if input_length is not None:
self.input_length = input_length
self.target_field_length = self.input_length - (
self.receptive_field_length - 1)
if target_field_length is not None:
self.target_field_length = target_field_length
self.input_length = self.receptive_field_length + (
self.target_field_length - 1)
else:
# sitas target field length of 1601 atrodo kaip magija, is kur jis gautas?
# target field length greiciui, turbut mazdaug random, bet nera svarbu manau
self.target_field_length = config['model']['target_field_length']
self.input_length = self.receptive_field_length + (
self.target_field_length - 1)
self.target_padding = config['model']['target_padding']
self.padded_target_field_length = self.target_field_length + 2 * self.target_padding
self.half_target_field_length = self.target_field_length // 2
self.half_receptive_field_length = self.receptive_field_length // 2
self.num_residual_blocks = len(self.dilations) * self.num_stacks
self.activation = keras.layers.Activation('relu')
self.samples_of_interest_indices = self.get_padded_target_field_indices(
)
self.target_sample_indices = self.get_target_field_indices()
self.optimizer = self.get_optimizer()
self.out_1_loss = self.get_out_1_loss()
self.out_2_loss = self.get_out_2_loss()
self.metrics = self.get_metrics()
self.epoch_num = 0
self.checkpoints_path = ''
self.samples_path = ''
self.history_filename = ''
self.config['model']['num_residual_blocks'] = self.num_residual_blocks
self.config['model'][
'receptive_field_length'] = self.receptive_field_length
self.config['model']['input_length'] = self.input_length
self.config['model']['target_field_length'] = self.target_field_length
self.model = self.setup_model(load_checkpoint, print_model_summary)
def __init__(self,
config,
load_checkpoint=None,
input_length=None,
target_field_length=None,
print_model_summary=False):
self.config = config
self.verbosity = config['training']['verbosity']
self.batch_size = config['training']['batch_size']
self.n_speaker = config['training'][
'n_speaker'] if 'n_speaker' in config['training'] else 2
self.n_output = config['training']['n_output'] if 'n_output' in config[
'training'] else 2
self.mute_other_channel = config['training'][
'mute_other_channel'] if 'mute_other_channel' in config[
'training'] else False
self.num_stacks = self.config['model']['num_stacks']
if type(self.config['model']['dilations']) is int:
self.dilations = [
2**i for i in range(0, self.config['model']['dilations'] + 1)
]
elif type(self.config['model']['dilations']) is list:
self.dilations = self.config['model']['dilations']
self.use_condition = config['training']['use_condition']
self.num_condition_classes = config['dataset']['num_condition_classes']
self.condition_input_length = self.get_condition_input_length(
self.config['model']['condition_encoding'])
# single target need how many input samples(must be odd)
self.receptive_field_length = util.compute_receptive_field_length(
config['model']['num_stacks'], self.dilations,
config['model']['filters']['lengths']['res'], 1)
print('Receptive Field Length:', self.receptive_field_length)
if input_length is not None:
self.input_length = input_length
self.target_field_length = self.input_length - (
self.receptive_field_length - 1)
if target_field_length is not None:
self.target_field_length = target_field_length
self.input_length = self.receptive_field_length + (
self.target_field_length - 1)
else:
self.target_field_length = config['model']['target_field_length']
self.input_length = self.receptive_field_length + (
self.target_field_length - 1)
self.input_length = int(self.input_length)
print('Input Length:', self.input_length)
self.target_padding = config['model']['target_padding']
self.padded_target_field_length = self.target_field_length + 2 * self.target_padding
self.half_target_field_length = self.target_field_length // 2
self.half_receptive_field_length = int(
self.receptive_field_length) // 2
self.num_residual_blocks = len(self.dilations) * self.num_stacks
self.activation = keras.layers.Activation('relu')
# self.activation = keras.layers.Activation('selu')
# self.activation = keras.layers.PReLU()
self.samples_of_interest_indices = self.get_padded_target_field_indices(
)
self.target_sample_indices = self.get_target_field_indices()
self.ozer_type = self.config['optimizer']['type']
self.optimizer = self.get_optimizer()
self.pit_loss = self.get_pit_loss()
self.metrics = self.get_metrics()
self.epoch_num = 0
self.checkpoints_path = ''
self.samples_path = ''
self.history_filename = ''
self.config['model']['num_residual_blocks'] = self.num_residual_blocks
self.config['model'][
'receptive_field_length'] = self.receptive_field_length
self.config['model']['input_length'] = self.input_length
self.config['model']['target_field_length'] = self.target_field_length
self.model = self.setup_model(load_checkpoint, print_model_summary)
def __init__(self,
config,
load_checkpoint=None,
input_length=None,
target_field_length=None,
print_model_summary=False):
self.config = config
self.verbosity = config['training']['verbosity']
#堆叠三层(num_stacks==3)
self.num_stacks = self.config['model']['num_stacks']
if type(self.config['model']['dilations']) is int:
#1,2,4,...,512重复三次
self.dilations = [
2**i for i in range(0, self.config['model']['dilations'] + 1)
]
elif type(self.config['model']['dilations']) is list:
self.dilations = self.config['model']['dilations']
#类别是29，应该是说话人鉴别，（一共28个说话人，加上一个unknown）
#self.num_condition_classes = config['dataset']['num_condition_classes']
#使用binary编码方式，这个长度计算出来是5，(因为29类用binary的编码方式5位就够了)
#self.condition_input_length = self.get_condition_input_length(self.config['model']['condition_encoding'])
#计算出来就是论文第四页的 6139 samples（对应一个output samples的输入感受野大小）
self.receptive_field_length = util.compute_receptive_field_length(
config['model']['num_stacks'], self.dilations,
config['model']['filters']['lengths']['res'], 1)
#这里的target field的大小是直接给出的，就是一次预测出多个samples（json中给的是1601）
if input_length is not None:
self.input_length = input_length
self.target_field_length = self.input_length - (
self.receptive_field_length - 1)
if target_field_length is not None:
self.target_field_length = target_field_length
self.input_length = self.receptive_field_length + (
self.target_field_length - 1)
#这里的代码是进入else选项 target_field_length == 1601
#receptive_field_length计算为6139(和论文中一致)
# ==>input_length == 6139 + 1601 - 1
#训练的时候使用的是最下面的这种模型
else:
self.target_field_length = config['model']['target_field_length']
self.input_length = self.receptive_field_length + (
self.target_field_length - 1)
#padding是在数据的周围补零吧
#padding的目的是让输入数据和输出数据的长度是相同的
self.target_padding = config['model']['target_padding']
self.padded_target_field_length = self.target_field_length + 2 * self.target_padding
#python3中是//表示变为整数
self.half_target_field_length = self.target_field_length // 2
self.half_receptive_field_length = self.receptive_field_length // 2
#residual block的数量
self.num_residual_blocks = len(self.dilations) * self.num_stacks
self.activation = layers.Activation('relu')
#加了padding的target范围
self.samples_of_interest_indices = self.get_padded_target_field_indices(
)
#不加padding的target范围
self.target_sample_indices = self.get_target_field_indices()
self.optimizer = self.get_optimizer()
self.out_1_loss = self.get_out_1_loss()
self.out_2_loss = self.get_out_2_loss()
self.metrics = self.get_metrics()
self.epoch_num = 0
self.checkpoints_path = ''
self.samples_path = ''
self.history_filename = ''
#后面这些参数在完成训练之后，写入到json文件中
self.config['model']['num_residual_blocks'] = self.num_residual_blocks
self.config['model'][
'receptive_field_length'] = self.receptive_field_length
self.config['model']['input_length'] = self.input_length
self.config['model']['target_field_length'] = self.target_field_length
self.model = self.setup_model(load_checkpoint, print_model_summary)