Sequential¶

class continual.Sequential(*args: Module)[source]¶

class continual.Sequential(arg: OrderedDict[str, Module])

A sequential container. This module is an augmentation of torch.nn.Sequential which adds continual inference methods

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(), forward_step() and forward_steps() methods of Sequential accept 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 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 applies to each of the modules it stores (which are each a registered submodule of the Sequential).

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 = co.Sequential(
    co.Conv2d(1,20,5),
    nn.ReLU(),
    co.Conv2d(20,64,5),
    nn.ReLU()
)

# Using Sequential with OrderedDict. This is functionally the
# same as the above code
model = co.Sequential(OrderedDict([
    ('conv1', co.Conv2d(1,20,5)),
    ('relu1', nn.ReLU()),
    ('conv2', co.Conv2d(20,64,5)),
    ('relu2', nn.ReLU())
]))

append(module)[source]¶

Appends a given module to the end.

Parameters:: module (nn.Module) – module to append
Return type:: Sequential