Containers#
SpikingJelly 的 容器 封装了常见的网络结构，并支持单步（s）和多步（m）步进模式。 欲获取更多详细信息，请参阅 包装器 。
SpikingJelly's containers wrap common network architectures and support both single-step (s) and multi-step (m) step modes. For more information, refer to Container .
- class spikingjelly.activation_based.layer.container.MultiStepContainer(*args)[源代码]#
基类：
Sequential,MultiStepModule
中文
中文
spikingjelly.activation_based.functional.multi_step_forward()的容器。构造方式与 torch.nn.Sequential 一致。
English
English
Container of
spikingjelly.activation_based.functional.multi_step_forward(). Its constructor signature is the same as torch.nn.Sequential.- 返回:
None
- 返回类型:
None
- forward(x_seq: Tensor)[源代码]#
- 参数:
x_seq (torch.Tensor) -- with shape
[T, batch_size, ...]- 返回:
y_seq with shape
[T, batch_size, ...]- 返回类型:
- class spikingjelly.activation_based.layer.container.SeqToANNContainer(*args)[源代码]#
基类：
Sequential,MultiStepModule
中文
中文
spikingjelly.activation_based.functional.seq_to_ann_forward()的容器。构造方式与 torch.nn.Sequential 一致。
English
English
Container of
spikingjelly.activation_based.functional.seq_to_ann_forward(). Its constructor signature is the same as torch.nn.Sequential.- 返回:
None
- 返回类型:
None
- forward(x_seq: Tensor)[源代码]#
- 参数:
x_seq (torch.Tensor) -- with shape
[T, batch_size, ...]- 返回:
y_seq with shape
[T, batch_size, ...]- 返回类型:
- class spikingjelly.activation_based.layer.container.TLastMultiStepContainer(*args)[源代码]#
基类：
Sequential,MultiStepModuleSee
spikingjelly.activation_based.functional.forward.t_last_multi_step_forward().- 返回:
None
- 返回类型:
None
- class spikingjelly.activation_based.layer.container.TLastSeqToANNContainer(*args)[源代码]#
基类：
Sequential,MultiStepModuleSee
spikingjelly.activation_based.functional.forward.t_last_seq_to_ann_forward().- 返回:
None
- 返回类型:
None
- class spikingjelly.activation_based.layer.container.StepModeContainer(stateful: bool, step_mode: str = 's', *args)[源代码]#
基类：
Sequential,StepModuleCall single-step forward, multi-step forward or seq-to-ANN forward according to
statefulandstep_mode.- 参数:
- 返回:
None
- 返回类型:
None
- class spikingjelly.activation_based.layer.container.ElementWiseRecurrentContainer(sub_module: Module, element_wise_function: Callable, step_mode='s')[源代码]#
基类：
MemoryModule
中文
使用逐元素运算的自连接包装器。记
sub_module的输入输出为 \(i[t]\) 和 \(y[t]\) （注意 \(y[t]\) 也是整个模块的输出）， 整个模块的输入为 \(x[t]\)，则\[i[t] = f(x[t], y[t-1])\]其中 \(f\) 是用户自定义的逐元素函数。我们默认 \(y[-1] = 0\)。
备注
sub_module输入和输出的尺寸需要相同。- 参数:
sub_module (torch.nn.Module) -- 被包含的模块
element_wise_function (Callable) -- 用户自定义的逐元素函数，应该形如
z=f(x, y)step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)
English
A container that use a element-wise recurrent connection. Denote the inputs and outputs of
sub_moduleas \(i[t]\) and \(y[t]\) (Note that \(y[t]\) is also the outputs of this module), and the inputs of this module as \(x[t]\), then\[i[t] = f(x[t], y[t-1])\]where \(f\) is the user-defined element-wise function. We set \(y[-1] = 0\).
Note
The shape of inputs and outputs of
sub_modulemust be the same.- 参数:
sub_module (torch.nn.Module) -- the contained module
element_wise_function (Callable) -- the user-defined element-wise function, which should have the format
z=f(x, y)step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)
代码示例 | Example
T = 8 net = ElementWiseRecurrentContainer( neuron.IFNode(v_reset=None), element_wise_function=lambda x, y: x + y ) print(net) x = torch.zeros([T]) x[0] = 1.5 for t in range(T): print(t, f"x[t]={x[t]}, s[t]={net(x[t])}") functional.reset_net(net)
- 返回:
None
- 返回类型:
None
- class spikingjelly.activation_based.layer.container.LinearRecurrentContainer(sub_module: Module, in_features: int, out_features: int, bias: bool = True, step_mode='s')[源代码]#
基类：
MemoryModule
中文
使用线性层的自连接包装器。记
sub_module的输入和输出为 \(i[t]\) 和 \(y[t]\) （注意 \(y[t]\) 也是整个模块的输出）， 整个模块的输入记作 \(x[t]\) ，则\[\begin{split}i[t] = \begin{pmatrix} x[t] \\ y[t-1]\end{pmatrix} W^{T} + b\end{split}\]其中 \(W, b\) 是线性层的权重和偏置项。默认 \(y[-1] = 0\)。
\(x[t]\) 应该
shape = [N, *, in_features]，\(y[t]\) 则应该shape = [N, *, out_features]。备注
自连接是由
torch.nn.Linear(in_features + out_features, in_features, bias)实现的。- 参数:
sub_module (torch.nn.Module) -- 被包含的模块
in_features (int) -- 输入的特征数量
out_features (int) -- 输出的特征数量
bias (bool) -- 若为
False，则线性自连接不会带有可学习的偏执项step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)
English
A container that use a linear recurrent connection. Denote the inputs and outputs of
sub_moduleas \(i[t]\) and \(y[t]\) (Note that \(y[t]\) is also the outputs of this module), and the inputs of this module as \(x[t]\), then\[\begin{split}i[t] = \begin{pmatrix} x[t] \\ y[t-1]\end{pmatrix} W^{T} + b\end{split}\]where \(W, b\) are the weight and bias of the linear connection. We set \(y[-1] = 0\).
\(x[t]\) should have the shape
[N, *, in_features], and \(y[t]\) has the shape[N, *, out_features].Note
The recurrent connection is implement by
torch.nn.Linear(in_features + out_features, in_features, bias).- 参数:
sub_module (torch.nn.Module) -- the contained module
in_features (int) -- size of each input sample
out_features (int) -- size of each output sample
bias (bool) -- If set to
False, the linear recurrent layer will not learn an additive biasstep_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)
代码示例 | Example
in_features = 4 out_features = 2 T = 8 N = 2 net = LinearRecurrentContainer( nn.Sequential( nn.Linear(in_features, out_features), neuron.LIFNode(), ), in_features, out_features, ) print(net) x = torch.rand([T, N, in_features]) for t in range(T): print(t, net(x[t])) functional.reset_net(net)
- 返回:
None
- 返回类型:
None