Hydra: competing convolutional kernels for fast and accurate time series classification.
This is a Pytorch implementation of Hydra-MultiRocket adapted by Ignacio Oguiza and based on:
Dempster, A., Schmidt, D. F., & Webb, G. I. (2023). Hydra: Competing convolutional kernels for fast and accurate time series classification. Data Mining and Knowledge Discovery, 1-27.
Original paper: https://link.springer.com/article/10.1007/s10618-023-00939-3
Original repository: https://github.com/angus924/hydra
Modules will be added to it in the order they are passed in the constructor. Alternatively, an OrderedDict of modules can be passed in. The forward() method of [Sequential](https://timeseriesAI.github.io/models.layers.html#sequential) accepts any input and forwards it to the first module it contains. It then “chains” outputs to inputs sequentially for each subsequent module, finally returning the output of the last module.
The value a [Sequential](https://timeseriesAI.github.io/models.layers.html#sequential) provides over manually calling a sequence of modules is that it allows treating the whole container as a single module, such that performing a transformation on the [Sequential](https://timeseriesAI.github.io/models.layers.html#sequential) applies to each of the modules it stores (which are each a registered submodule of the [Sequential](https://timeseriesAI.github.io/models.layers.html#sequential)).
What’s the difference between a [Sequential](https://timeseriesAI.github.io/models.layers.html#sequential) and a :class:torch.nn.ModuleList? A ModuleList is exactly what it sounds like–a list for storing Module s! On the other hand, the layers in a [Sequential](https://timeseriesAI.github.io/models.layers.html#sequential) are connected in a cascading way.
Example::
# Using Sequential to create a small model. When `model` is run,
# input will first be passed to `Conv2d(1,20,5)`. The output of
# `Conv2d(1,20,5)` will be used as the input to the first
# `ReLU`; the output of the first `ReLU` will become the input
# for `Conv2d(20,64,5)`. Finally, the output of
# `Conv2d(20,64,5)` will be used as input to the second `ReLU`
model = nn.Sequential(
nn.Conv2d(1,20,5),
nn.ReLU(),
nn.Conv2d(20,64,5),
nn.ReLU()
)
# Using Sequential with OrderedDict. This is functionally the
# same as the above code
model = nn.Sequential(OrderedDict([
('conv1', nn.Conv2d(1,20,5)),
('relu1', nn.ReLU()),
('conv2', nn.Conv2d(20,64,5)),
('relu2', nn.ReLU())
]))
Type
Default
Details
c_in
int
num of channels in input
c_out
int
num of channels in output
seq_len
int
sequence length
d
tuple
None
shape of the output (when ndim > 1)
k
int
8
number of kernels per group in HydraBackbone
g
int
64
number of groups in HydraBackbone
max_c_in
int
8
max number of channels per group in HydraBackbone
clip
bool
True
clip values >= 0 in HydraBackbone
num_features
int
50000
number of MultiRocket features
max_dilations_per_kernel
int
32
max dilations per kernel in MultiRocket
kernel_size
int
9
kernel size in MultiRocket
max_num_channels
int
None
max number of channels in MultiRocket
max_num_kernels
int
84
max number of kernels in MultiRocket
use_bn
bool
True
use batch norm
fc_dropout
float
0.0
dropout probability
custom_head
typing.Any
None
optional custom head as a torch.nn.Module or Callable