def __init__(self, encoder, dropout_rate=0.5) -> None:
super().__init__()
self.encoder = encoder_params[encoder]["init_op"]()
self.avg_pool = AdaptiveAvgPool2d((1, 1))
self.srm_conv = setup_srm_layer(3)
self.dropout = Dropout(dropout_rate)
self.fc = Linear(encoder_params[encoder]["features"], 1)
def __init__(self, encoder, dropout_rate=0.0,out_dim=56) -> None:
super().__init__()
self.encoder = encoder_params[encoder]["init_op"]()
self.avg_pool = AdaptiveAvgPool2d((1, 1))
self.dropout = Dropout(dropout_rate)
self.out_dim = out_dim
self.fc = Linear(encoder_params[encoder]["features"], out_dim)
def __init__(self, encoder, name='', dropout_rate=0.0) -> None:
super().__init__()
self.name = name
self.encoder = encoder_params[encoder]["init_op"]()
self.avg_pool = AdaptiveAvgPool2d((1, 1))
self.dropout = Dropout(dropout_rate)
self.fc = Linear(encoder_params[encoder]["features"], 1)
def __init__(self, encoder, nclasses, dropout_rate=0.0, infer = False) -> None:
super().__init__()
self.encoder = encoder_params[encoder]["init_op"]()
self.avg_pool = AdaptiveAvgPool2d((1, 1))
self.dropout = Dropout(dropout_rate)
self.fc = Linear(encoder_params[encoder]["features"], nclasses)
self.infer = infer
def __init__(self, encoder, dropout_rate=0.5) -> None:
super().__init__()
self.decoder = Decoder(decoder_filters=encoder_params[encoder]["decoder_filters"],
filters=encoder_params[encoder]["filters"])
self.avg_pool = AdaptiveAvgPool2d((1, 1))
self.dropout = Dropout(dropout_rate)
self.fc = Linear(encoder_params[encoder]["features"], 1)
self.final = Conv2d(encoder_params[encoder]["decoder_filters"][0], out_channels=1, kernel_size=1, bias=False)
_initialize_weights(self)
self.encoder = encoder_params[encoder]["init_op"]()
def __init__(self, encoder, sample_rate, window_size, hop_size, mel_bins,
fmin, fmax, classes_num):
super().__init__()
window = 'hann'
center = True
pad_mode = 'reflect'
ref = 1.0
amin = 1e-10
top_db = None
# Spectrogram extractor
self.spectrogram_extractor = Spectrogram(n_fft=window_size,
hop_length=hop_size,
win_length=window_size,
window=window,
center=center,
pad_mode=pad_mode,
freeze_parameters=True)
# Logmel feature extractor
self.logmel_extractor = LogmelFilterBank(sr=sample_rate,
n_fft=window_size,
n_mels=mel_bins,
fmin=fmin,
fmax=fmax,
ref=ref,
amin=amin,
top_db=top_db,
freeze_parameters=True)
# Spec augmenter
self.spec_augmenter = SpecAugmentation(time_drop_width=64,
time_stripes_num=2,
freq_drop_width=8,
freq_stripes_num=2)
self.encoder = encoder_params[encoder]["init_op"]()
self.avg_pool = AdaptiveAvgPool2d((1, 1))
#self.max_pool = AdaptiveMaxPool2d((1, 1))
self.dropout = Dropout(0.3)
self.fc = Linear(encoder_params[encoder]['features'], classes_num)
def __init__(self, encoder, dropout_rate=0.0):
super().__init__()
self.encoder = encoder_params[encoder]["base_net"]()
self.avg_pool = AdaptiveAvgPool2d((1, 1))
self.dropout = Dropout(dropout_rate)
self.fc = Linear(encoder_params[encoder]["features"], 1)
def __init__(self, encoder, encoder_features, dropout_rate=0.0):
super().__init__()
self.encoder = encoder
self.avg_pool = AdaptiveAvgPool2d((1, 1))
self.dropout = Dropout(dropout_rate)
self.fc = Linear(encoder_features, 1)
