def __init__(
self,
inp_filters: int,
out_filters: int,
group_scale: int = 8,
se_channels: int = 128,
kernel_size: int = 1,
dilation: int = 1,
init_mode: str = 'xavier_uniform',
):
super().__init__()
self.out_filters = out_filters
padding_val = get_same_padding(kernel_size=kernel_size,
dilation=dilation,
stride=1)
group_conv = nn.Conv1d(
out_filters,
out_filters,
kernel_size=kernel_size,
dilation=dilation,
padding=padding_val,
groups=group_scale,
)
self.group_tdnn_block = nn.Sequential(
TDNNModule(inp_filters, out_filters, kernel_size=1, dilation=1),
group_conv,
nn.ReLU(),
nn.BatchNorm1d(out_filters),
TDNNModule(out_filters, out_filters, kernel_size=1, dilation=1),
)
self.se_layer = MaskedSEModule(out_filters, se_channels, out_filters)
self.apply(lambda x: init_weights(x, mode=init_mode))
def __init__(
self,
inp_filters: int,
out_filters: int,
kernel_size: int = 1,
dilation: int = 1,
stride: int = 1,
padding: int = None,
):
super().__init__()
if padding is None:
padding = get_same_padding(kernel_size,
stride=stride,
dilation=dilation)
self.conv_layer = nn.Conv1d(
in_channels=inp_filters,
out_channels=out_filters,
kernel_size=kernel_size,
dilation=dilation,
padding=padding,
)
self.activation = nn.ReLU()
self.bn = nn.BatchNorm1d(out_filters)
def test_padding_size_conv1d(self):
input_channels = 1
output_channels = 1
kernel_sizes = [3, 7, 11]
dilation_sizes = [2, 3, 4]
stride = 1
inp = torch.rand(2, 1, 40)
for kernel_size in kernel_sizes:
for dilation_size in dilation_sizes:
padding = jasper.get_same_padding(kernel_size, stride, dilation_size)
conv = torch.nn.Conv1d(
input_channels, output_channels, kernel_size=kernel_size, dilation=dilation_size, padding=padding
)
out = conv(inp)
assert out.shape == inp.shape