def __init__(self, hparams):
super(Spotify, self).__init__()
self.conv0 = nn.Sequential(
nn.Conv1d(hparams.num_mels, 32, kernel_size=4, stride=1, padding=0),
nn.BatchNorm1d(32),
nn.LeakyReLU(),
nn.MaxPool1d(8, stride=8)
)
self.conv1 = nn.Sequential(
nn.Conv1d(32, 32, kernel_size=4, stride=1, padding=0),
nn.BatchNorm1d(32),
nn.LeakyReLU(),
nn.MaxPool1d(4, stride=4)
)
self.conv2 = nn.Sequential(
nn.Conv1d(32, 64, kernel_size=4, stride=1, padding=0),
nn.BatchNorm1d(64),
nn.LeakyReLU(),
nn.MaxPool1d(4, stride=4)
)
self.pool0 = nn.AvgPool1d(4, stride=4)
self.pool1 = nn.MaxPool1d(4, stride=4)
self.pool2 = nn.LPPool1d(2, kernel_size=4, stride=4)
self.pool3 = nn.LPPool1d(1, kernel_size=4, stride=4)
self.fc1 = nn.Sequential(
nn.Dropout(0.3),
nn.Linear(192, 64)
)
self.fc2 = nn.Linear(64, 64)
self.fc3 = nn.Linear(64, len(hparams.genres))
def __init__(self):
super(NNPoolingModule, self).__init__()
self.input1d = torch.randn(1, 16, 50)
self.module1d = nn.ModuleList([
nn.MaxPool1d(3, stride=2),
nn.AvgPool1d(3, stride=2),
nn.LPPool1d(2, 3, stride=2),
nn.AdaptiveMaxPool1d(3),
nn.AdaptiveAvgPool1d(3),
])
self.input2d = torch.randn(1, 16, 30, 10)
self.module2d = nn.ModuleList([
nn.MaxPool2d((3, 2), stride=(2, 1)),
nn.AvgPool2d((3, 2), stride=(2, 1)),
nn.FractionalMaxPool2d(3, output_ratio=(0.5, 0.5)),
nn.LPPool2d(2, 3, stride=(2, 1)),
nn.AdaptiveMaxPool2d((5, 7)),
nn.AdaptiveAvgPool2d((7)),
])
self.input3d = torch.randn(1, 16, 20, 4, 4)
self.module3d = nn.ModuleList([
nn.MaxPool3d(2),
nn.AvgPool3d(2),
nn.FractionalMaxPool3d(2, output_ratio=(0.5, 0.5, 0.5)),
nn.AdaptiveMaxPool3d((5, 7, 9)),
nn.AdaptiveAvgPool3d((5, 7, 9)),
])
def forward(self, src_tokens, src_lengths, prev_output_tokens):
encoder_out = self.encoder(src_tokens, src_lengths)
decoder_out = self.decoder(prev_output_tokens, encoder_out)
if self.prop_predict:
if 'pool' in self.fp_type:
fp = encoder_out['encoder_out']
seqz, bsz, csz = fp.shape
if self.fp_type == 'avgpool':
pool = nn.AvgPool1d(seqz)
elif self.fp_type == 'maxpool':
pool = nn.MaxPool1d(seqz)
else:
pool = nn.LPPool1d(2, seqz)
fp = torch.transpose(torch.transpose(fp, 0, 1), 1, 2)
fp = pool(fp)
fp = fp.contiguous().view(bsz, csz)
else: # 'first'
# Use the encoder output of the first token <GO> as FP.
fp = encoder_out['encoder_out'][0, :, :]
if self.get_fp:
return fp
pred_out = self.prednet(fp)
return decoder_out, pred_out
else:
return decoder_out
def __init__(self):
super(Model, self).__init__()
self.pool_0 = nn.LPPool1d(norm_type=2, kernel_size=3)
self.pool_1 = nn.LPPool1d(norm_type=2, kernel_size=4, stride=2)
self.pool_2 = nn.LPPool1d(norm_type=1, kernel_size=3, stride=1, ceil_mode=False)
self.pool_3 = nn.LPPool1d(norm_type=1, kernel_size=5, stride=1, ceil_mode=True)
self.pool_4 = nn.LPPool1d(norm_type=1.2, kernel_size=3, stride=2, ceil_mode=False)
self.pool_5 = nn.LPPool1d(norm_type=0.5, kernel_size=2, stride=1, ceil_mode=True)
self.pool_6 = nn.LPPool1d(norm_type=0.1, kernel_size=4, stride=1, ceil_mode=False)
def __init__(self,
mode,
nfilters,
samplerate=16000,
wlen=25,
wstride=10,
compression='log',
preemp=False,
mvn=False):
super(TDFbanks, self).__init__()
window_size = samplerate * wlen // 1000 + 1
window_stride = samplerate * wstride // 1000
padding_size = (window_size - 1) // 2
self.preemp = None
if preemp:
self.preemp = nn.Conv1d(1,
1,
2,
1,
padding=1,
groups=1,
bias=False)
self.complex_conv = nn.Conv1d(1,
2 * nfilters,
window_size,
1,
padding=padding_size,
groups=1,
bias=False)
self.modulus = nn.LPPool1d(2, 2, stride=2)
self.lowpass = nn.Conv1d(nfilters,
nfilters,
window_size,
window_stride,
padding=0,
groups=nfilters,
bias=False)
if mode == 'Fixed':
for param in self.parameters():
param.requires_grad = False
elif mode == 'learnfbanks':
if preemp:
self.preemp.weight.requires_grad = False
self.lowpass.weight.requires_grad = False
if mvn:
self.instancenorm = nn.InstanceNorm1d(nfilters, momentum=1)
self.nfilters = nfilters
self.fs = samplerate
self.wlen = wlen
self.wstride = wstride
self.compression = compression
self.mvn = mvn
def __init__(self, args):
super().__init__()
self.args = args
self.original_len = args.window_size
self.latent_len = int(self.original_len / 2)
self.dropout_rate = args.drop_out
self.hidden = 256
self.heads = 2
self.n_layers = 2
self.output_size = args.output_size
self.conv = nn.Conv1d(in_channels=1,
out_channels=self.hidden,
kernel_size=5,
stride=1,
padding=2,
padding_mode='replicate')
self.pool = nn.LPPool1d(norm_type=2, kernel_size=2, stride=2)
self.position = PositionalEmbedding(max_len=self.latent_len,
d_model=self.hidden)
self.layer_norm = LayerNorm(self.hidden)
self.dropout = nn.Dropout(p=self.dropout_rate)
self.transformer_blocks = nn.ModuleList([
TransformerBlock(self.hidden, self.heads, self.hidden * 4,
self.dropout_rate) for _ in range(self.n_layers)
])
self.deconv = nn.ConvTranspose1d(in_channels=self.hidden,
out_channels=self.hidden,
kernel_size=4,
stride=2,
padding=1)
self.linear1 = nn.Linear(self.hidden, 128)
self.linear2 = nn.Linear(128, self.output_size)
self.truncated_normal_init()
#%% unpool(out, indices) ##恢复为原先的形状，除最大元素外，其他元素为 0 #%% #>3. 平均池化 ##>3.1 二维平均池化 m = nn.AvgPool2d((3, 2), stride=(2, 1)) input = torch.randn(20, 16, 50, 32) out = m(input) out.shape #%% #>4. LP范数池化 input = torch.arange(1, 5, dtype=torch.float).reshape(1, 1, 4) pool = nn.LPPool1d(2, 2) ##取2-范数，核为2，其他参数默认 out = pool(input) out #%% #>5. 自适应最大池化 #%% [markdown] # - 自适应最大池化只需要指定输出的目标尺寸即可，其他参数自动计算 #%% ##>5.1 一维自适应最大池化 input = torch.randn(1, 64, 8) m = nn.AdaptiveMaxPool1d(5) #目标尺寸为5 out = m(input) out.shape
def __append_layer(self, net_style, args_dict):
args_values_list = list(args_dict.values())
if net_style == "Conv2d":
self.layers.append(
nn.Conv2d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5],
args_values_list[6], args_values_list[7]))
elif net_style == "MaxPool2d":
self.layers.append(
nn.MaxPool2d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5]))
elif net_style == "Linear":
self.layers.append(
nn.Linear(args_values_list[0], args_values_list[1],
args_values_list[2]))
elif net_style == "reshape":
# 如果是特殊情况 reshape，就直接将目标向量尺寸传入
# print(type(args_values_list[0]))
self.layers.append(args_values_list[0])
elif net_style == "Conv1d":
self.layers.append(
nn.Conv1d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5],
args_values_list[6], args_values_list[7]))
elif net_style == "Conv3d":
self.layers.append(
nn.Conv3d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5],
args_values_list[6], args_values_list[7]))
elif net_style == "ConvTranspose1d":
self.layers.append(
nn.ConvTranspose1d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5],
args_values_list[6], args_values_list[7],
args_values_list[8]))
elif net_style == "ConvTranspose2d":
self.layers.append(
nn.ConvTranspose2d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5],
args_values_list[6], args_values_list[7],
args_values_list[8]))
elif net_style == "ConvTranspose3d":
self.layers.append(
nn.ConvTranspose3d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5],
args_values_list[6], args_values_list[7],
args_values_list[8]))
elif net_style == "Unfold":
self.layers.append(
nn.Unfold(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3]))
elif net_style == "Fold":
self.layers.append(
nn.Unfold(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "MaxPool1d":
self.layers.append(
nn.MaxPool1d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5]))
elif net_style == "MaxPool3d":
self.layers.append(
nn.MaxPool3d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4], args_values_list[5]))
elif net_style == "MaxUnpool1d":
self.layers.append(
nn.MaxUnpool1d(args_values_list[0], args_values_list[1],
args_values_list[2]))
elif net_style == "MaxUnpool2d":
self.layers.append(
nn.MaxUnpool2d(args_values_list[0], args_values_list[1],
args_values_list[2]))
elif net_style == "MaxUnpool3d":
self.layers.append(
nn.MaxUnpool3d(args_values_list[0], args_values_list[1],
args_values_list[2]))
elif net_style == "AvgPool1d":
self.layers.append(
nn.AvgPool1d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "AvgPool2d":
self.layers.append(
nn.AvgPool2d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "AvgPool3d":
self.layers.append(
nn.AvgPool3d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "FractionalMaxPool2d":
self.layers.append(
nn.FractionalMaxPool2d(args_values_list[0],
args_values_list[1],
args_values_list[2],
args_values_list[3],
args_values_list[4]))
elif net_style == "LPPool1d":
self.layers.append(
nn.LPPool1d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3]))
elif net_style == "LPPool2d":
self.layers.append(
nn.LPPool2d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3]))
elif net_style == "AdaptiveMaxPool1d":
self.layers.append(
nn.AdaptiveMaxPool1d(args_values_list[0], args_values_list[1]))
elif net_style == "AdaptiveMaxPool2d":
self.layers.append(
nn.AdaptiveMaxPool2d(args_values_list[0], args_values_list[1]))
elif net_style == "AdaptiveMaxPool3d":
self.layers.append(
nn.AdaptiveMaxPool3d(args_values_list[0], args_values_list[1]))
elif net_style == "AdaptiveAvgPool1d":
self.layers.append(nn.AdaptiveAvgPool1d(args_values_list[0]))
elif net_style == "AdaptiveAvgPool2d":
self.layers.append(nn.AdaptiveAvgPool2d(args_values_list[0]))
elif net_style == "AdaptiveAvgPool3d":
self.layers.append(nn.AdaptiveAvgPool3d(args_values_list[0]))
elif net_style == "ReflectionPad1d":
self.layers.append(nn.ReflectionPad1d(args_values_list[0]))
elif net_style == "ReflectionPad2d":
self.layers.append(nn.ReflectionPad2d(args_values_list[0]))
elif net_style == "ReplicationPad1d":
self.layers.append(nn.ReplicationPad1d(args_values_list[0]))
elif net_style == "ReplicationPad2d":
self.layers.append(nn.ReplicationPad2d(args_values_list[0]))
elif net_style == "ReplicationPad3d":
self.layers.append(nn.ReplicationPad3d(args_values_list[0]))
elif net_style == "ZeroPad2d":
self.layers.append(nn.ZeroPad2d(args_values_list[0]))
elif net_style == "ConstantPad1d":
self.layers.append(
nn.ConstantPad1d(args_values_list[0], args_values_list[1]))
elif net_style == "ConstantPad2d":
self.layers.append(
nn.ConstantPad2d(args_values_list[0], args_values_list[1]))
elif net_style == "ConstantPad3d":
self.layers.append(
nn.ConstantPad3d(args_values_list[0], args_values_list[1]))
elif net_style == "ELU":
self.layers.append(nn.ELU(args_values_list[0],
args_values_list[1]))
elif net_style == "Hardshrink":
self.layers.append(nn.Hardshrink(args_values_list[0]))
elif net_style == "Hardtanh":
self.layers.append(
nn.Hardtanh(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "LeakyReLU":
self.layers.append(
nn.LeakyReLU(args_values_list[0], args_values_list[1]))
elif net_style == "LogSigmoid":
self.layers.append(nn.LogSigmoid())
elif net_style == "PReLU":
self.layers.append(
nn.PReLU(args_values_list[0], args_values_list[1]))
elif net_style == "ReLU":
self.layers.append(nn.ReLU(args_values_list[0]))
elif net_style == "ReLU6":
self.layers.append(nn.ReLU6(args_values_list[0]))
elif net_style == "RReLU":
self.layers.append(
nn.RReLU(args_values_list[0], args_values_list[1],
args_values_list[2]))
elif net_style == "SELU":
self.layers.append(nn.SELU(args_values_list[0]))
elif net_style == "CELU":
self.layers.append(
nn.CELU(args_values_list[0], args_values_list[1]))
elif net_style == "Sigmoid":
self.layers.append(nn.Sigmoid())
elif net_style == "Softplus":
self.layers.append(
nn.Softplus(args_values_list[0], args_values_list[1]))
elif net_style == "Softshrink":
self.layers.append(nn.Softshrink(args_values_list[0]))
elif net_style == "Softsign":
self.layers.append(nn.Softsign())
elif net_style == "Tanh":
self.layers.append(nn.Tanh())
elif net_style == "Tanhshrink":
self.layers.append(nn.Tanhshrink())
elif net_style == "Threshold":
self.layers.append(
nn.Threshold(args_values_list[0], args_values_list[1],
args_values_list[2]))
elif net_style == "Softmin":
self.layers.append(nn.Softmin(args_values_list[0]))
elif net_style == "Softmax":
self.layers.append(nn.Softmax(args_values_list[0]))
elif net_style == "Softmax2d":
self.layers.append(nn.Softmax2d())
elif net_style == "LogSoftmax":
self.layers.append(nn.LogSoftmax(args_values_list[0]))
elif net_style == "AdaptiveLogSoftmaxWithLoss":
self.layers.append(
nn.AdaptiveLogSoftmaxWithLoss(args_values_list[0],
args_values_list[1],
args_values_list[2],
args_values_list[3],
args_values_list[4]))
elif net_style == "BatchNorm1d":
self.layers.append(
nn.BatchNorm1d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "BatchNorm2d":
self.layers.append(
nn.BatchNorm2d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "BatchNorm3d":
self.layers.append(
nn.BatchNorm3d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "GroupNorm":
self.layers.append(
nn.GroupNorm(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3]))
elif net_style == "InstanceNorm1d":
self.layers.append(
nn.InstanceNorm1d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "InstanceNorm2d":
self.layers.append(
nn.InstanceNorm2d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "InstanceNorm3d":
self.layers.append(
nn.InstanceNorm3d(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3],
args_values_list[4]))
elif net_style == "LayerNorm":
self.layers.append(
nn.LayerNorm(args_values_list[0], args_values_list[1],
args_values_list[2]))
elif net_style == "LocalResponseNorm":
self.layers.append(
nn.LocalResponseNorm(args_values_list[0], args_values_list[1],
args_values_list[2], args_values_list[3]))
elif net_style == "Linear":
self.layers.append(
nn.Linear(args_values_list[0], args_values_list[1],
args_values_list[2]))
elif net_style == "Dropout":
self.layers.append(
nn.Dropout(args_values_list[0], args_values_list[1]))
elif net_style == "Dropout2d":
self.layers.append(
nn.Dropout2d(args_values_list[0], args_values_list[1]))
elif net_style == "Dropout3d":
self.layers.append(
nn.Dropout3d(args_values_list[0], args_values_list[1]))
elif net_style == "AlphaDropout":
self.layers.append(
nn.AlphaDropout(args_values_list[0], args_values_list[1]))