This is an unofficial PyTorch implementation by Ignacio Oguiza - oguiza@gmail.com based on:
class InceptionModule[source]
InceptionModule(ni,nf,ks=40,bottleneck=True) ::Module
Same as nn.Module, but no need for subclasses to call super().__init__
class InceptionBlock[source]
InceptionBlock(ni,nf=32,residual=True,depth=6,ks=40,bottleneck=True) ::Module
Same as nn.Module, but no need for subclasses to call super().__init__
class InceptionTime[source]
InceptionTime(c_in,c_out,nf=32,nb_filters=None,ks=40,bottleneck=True) ::Module
Same as nn.Module, but no need for subclasses to call super().__init__
bs = 16
vars = 1
seq_len = 12
c_out = 2
xb = torch.rand(bs, vars, seq_len)
test_eq(InceptionTime(vars,c_out)(xb).shape, [bs, c_out])
test_eq(InceptionTime(vars,c_out, bottleneck=False)(xb).shape, [bs, c_out])
test_eq(InceptionTime(vars,c_out, residual=False)(xb).shape, [bs, c_out])
test_eq(total_params(InceptionTime(3, 2))[0], 455490)
InceptionTime(3,2)
InceptionTime(
(inceptionblock): InceptionBlock(
(inception): ModuleList(
(0): InceptionModule(
(bottleneck): Conv1d(3, 32, kernel_size=(1,), stride=(1,), bias=False)
(convs): ModuleList(
(0): Conv1d(32, 32, kernel_size=(39,), stride=(1,), padding=(19,), bias=False)
(1): Conv1d(32, 32, kernel_size=(19,), stride=(1,), padding=(9,), bias=False)
(2): Conv1d(32, 32, kernel_size=(9,), stride=(1,), padding=(4,), bias=False)
)
(maxconvpool): Sequential(
(0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv1d(3, 32, kernel_size=(1,), stride=(1,), bias=False)
)
(concat): Concat(dim=1)
(bn): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): ReLU()
)
(1): InceptionModule(
(bottleneck): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
(convs): ModuleList(
(0): Conv1d(32, 32, kernel_size=(39,), stride=(1,), padding=(19,), bias=False)
(1): Conv1d(32, 32, kernel_size=(19,), stride=(1,), padding=(9,), bias=False)
(2): Conv1d(32, 32, kernel_size=(9,), stride=(1,), padding=(4,), bias=False)
)
(maxconvpool): Sequential(
(0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
)
(concat): Concat(dim=1)
(bn): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): ReLU()
)
(2): InceptionModule(
(bottleneck): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
(convs): ModuleList(
(0): Conv1d(32, 32, kernel_size=(39,), stride=(1,), padding=(19,), bias=False)
(1): Conv1d(32, 32, kernel_size=(19,), stride=(1,), padding=(9,), bias=False)
(2): Conv1d(32, 32, kernel_size=(9,), stride=(1,), padding=(4,), bias=False)
)
(maxconvpool): Sequential(
(0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
)
(concat): Concat(dim=1)
(bn): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): ReLU()
)
(3): InceptionModule(
(bottleneck): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
(convs): ModuleList(
(0): Conv1d(32, 32, kernel_size=(39,), stride=(1,), padding=(19,), bias=False)
(1): Conv1d(32, 32, kernel_size=(19,), stride=(1,), padding=(9,), bias=False)
(2): Conv1d(32, 32, kernel_size=(9,), stride=(1,), padding=(4,), bias=False)
)
(maxconvpool): Sequential(
(0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
)
(concat): Concat(dim=1)
(bn): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): ReLU()
)
(4): InceptionModule(
(bottleneck): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
(convs): ModuleList(
(0): Conv1d(32, 32, kernel_size=(39,), stride=(1,), padding=(19,), bias=False)
(1): Conv1d(32, 32, kernel_size=(19,), stride=(1,), padding=(9,), bias=False)
(2): Conv1d(32, 32, kernel_size=(9,), stride=(1,), padding=(4,), bias=False)
)
(maxconvpool): Sequential(
(0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
)
(concat): Concat(dim=1)
(bn): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): ReLU()
)
(5): InceptionModule(
(bottleneck): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
(convs): ModuleList(
(0): Conv1d(32, 32, kernel_size=(39,), stride=(1,), padding=(19,), bias=False)
(1): Conv1d(32, 32, kernel_size=(19,), stride=(1,), padding=(9,), bias=False)
(2): Conv1d(32, 32, kernel_size=(9,), stride=(1,), padding=(4,), bias=False)
)
(maxconvpool): Sequential(
(0): MaxPool1d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(1): Conv1d(128, 32, kernel_size=(1,), stride=(1,), bias=False)
)
(concat): Concat(dim=1)
(bn): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(act): ReLU()
)
)
(shortcut): ModuleList(
(0): ConvBlock(
(0): Conv1d(3, 128, kernel_size=(1,), stride=(1,), bias=False)
(1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(1): BatchNorm1d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(add): Add
(act): ReLU()
)
(gap): GAP1d(
(gap): AdaptiveAvgPool1d(output_size=1)
(flatten): Flatten(full=False)
)
(fc): Linear(in_features=128, out_features=2, bias=True)
)