Wrappers for Stateless Layers#

SpikingJelly 的 无状态层包装器 封装了 PyTorch 的标准层，并支持脉冲神经网络的时间步进模式。欲获取更多信息，请查看基本概念。

SpikingJelly's stateless layer wrappers wrap PyTorch's standard layers and support the step mode of Spiking Neural Networks. See Basic Conception for more details.

class spikingjelly.activation_based.layer.stateless_wrapper.Conv1d(in_channels: int, out_channels: int, kernel_size: int | tuple[int], stride: int | tuple[int] = 1, padding: str | int | tuple[int] = 0, dilation: int | tuple[int] = 1, groups: int = 1, bias: bool = True, padding_mode: str = 'zeros', step_mode: str = 's')[源代码]#

基类：Conv1d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.Conv1d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.Conv1d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.Conv2d(in_channels: int, out_channels: int, kernel_size: int | tuple[int, int], stride: int | tuple[int, int] = 1, padding: str | int | tuple[int, int] = 0, dilation: int | tuple[int, int] = 1, groups: int = 1, bias: bool = True, padding_mode: str = 'zeros', step_mode: str = 's')[源代码]#

基类：Conv2d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.Conv2d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.Conv2d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.Conv3d(in_channels: int, out_channels: int, kernel_size: int | tuple[int, int, int], stride: int | tuple[int, int, int] = 1, padding: str | int | tuple[int, int, int] = 0, dilation: int | tuple[int, int, int] = 1, groups: int = 1, bias: bool = True, padding_mode: str = 'zeros', step_mode: str = 's')[源代码]#

基类：Conv3d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.Conv3d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.Conv3d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.Upsample(size: int | tuple[int, ...] | None = None, scale_factor: float | tuple[float, ...] | None = None, mode: str = 'nearest', align_corners: bool | None = None, recompute_scale_factor: bool | None = None, step_mode: str = 's')[源代码]#

基类：Upsample, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.Upsample

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.Upsample for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor) → Tensor[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.ConvTranspose1d(in_channels: int, out_channels: int, kernel_size: int | tuple[int], stride: int | tuple[int] = 1, padding: int | tuple[int] = 0, output_padding: int | tuple[int] = 0, groups: int = 1, bias: bool = True, dilation: int | tuple[int] = 1, padding_mode: str = 'zeros', step_mode: str = 's')[源代码]#

基类：ConvTranspose1d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.ConvTranspose1d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.ConvTranspose1d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.ConvTranspose2d(in_channels: int, out_channels: int, kernel_size: int | tuple[int, int], stride: int | tuple[int, int] = 1, padding: int | tuple[int, int] = 0, output_padding: int | tuple[int, int] = 0, groups: int = 1, bias: bool = True, dilation: int = 1, padding_mode: str = 'zeros', step_mode: str = 's')[源代码]#

基类：ConvTranspose2d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.ConvTranspose2d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.ConvTranspose2d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.ConvTranspose3d(in_channels: int, out_channels: int, kernel_size: int | tuple[int, int, int], stride: int | tuple[int, int, int] = 1, padding: int | tuple[int, int, int] = 0, output_padding: int | tuple[int, int, int] = 0, groups: int = 1, bias: bool = True, dilation: int | tuple[int, int, int] = 1, padding_mode: str = 'zeros', step_mode: str = 's')[源代码]#

基类：ConvTranspose3d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.ConvTranspose3d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.ConvTranspose3d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.GroupNorm(num_groups: int, num_channels: int, eps: float = 1e-05, affine: bool = True, step_mode='s')[源代码]#

基类：GroupNorm, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.GroupNorm

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.GroupNorm for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.MaxPool1d(kernel_size: int | tuple[int], stride: int | tuple[int] | None = None, padding: int | tuple[int] = 0, dilation: int | tuple[int] = 1, return_indices: bool = False, ceil_mode: bool = False, step_mode='s')[源代码]#

基类：MaxPool1d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.MaxPool1d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.MaxPool1d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.MaxPool2d(kernel_size: int | tuple[int, int], stride: int | tuple[int, int] | None = None, padding: int | tuple[int, int] = 0, dilation: int | tuple[int, int] = 1, return_indices: bool = False, ceil_mode: bool = False, step_mode='s')[源代码]#

基类：MaxPool2d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.MaxPool2d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.MaxPool2d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.MaxPool3d(kernel_size: int | tuple[int, int, int], stride: int | tuple[int, int, int] | None = None, padding: int | tuple[int, int, int] = 0, dilation: int | tuple[int, int, int] = 1, return_indices: bool = False, ceil_mode: bool = False, step_mode='s')[源代码]#

基类：MaxPool3d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.MaxPool3d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.MaxPool3d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.AvgPool1d(kernel_size: int | tuple[int], stride: int | tuple[int] = None, padding: int | tuple[int] = 0, ceil_mode: bool = False, count_include_pad: bool = True, step_mode='s')[源代码]#

基类：AvgPool1d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.AvgPool1d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.AvgPool1d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.AvgPool2d(kernel_size: int | tuple[int, int], stride: int | tuple[int, int] | None = None, padding: int | tuple[int, int] = 0, ceil_mode: bool = False, count_include_pad: bool = True, divisor_override: int | None = None, step_mode='s')[源代码]#

基类：AvgPool2d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.AvgPool2d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.AvgPool2d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.AvgPool3d(kernel_size: int | tuple[int, int, int], stride: int | tuple[int, int, int] | None = None, padding: int | tuple[int, int, int] = 0, ceil_mode: bool = False, count_include_pad: bool = True, divisor_override: int | None = None, step_mode='s')[源代码]#

基类：AvgPool3d, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.AvgPool3d

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.AvgPool3d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.AdaptiveAvgPool1d(output_size, step_mode='s')[源代码]#

基类：AdaptiveAvgPool1d, StepModule

API Language: 中文 | English

中文
中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.AdaptiveAvgPool1d

English
English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.AdaptiveAvgPool1d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.AdaptiveAvgPool2d(output_size, step_mode='s')[源代码]#

基类：AdaptiveAvgPool2d, StepModule

API Language: 中文 | English

中文
中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.AdaptiveAvgPool2d

English
English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.AdaptiveAvgPool2d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.AdaptiveAvgPool3d(output_size, step_mode='s')[源代码]#

基类：AdaptiveAvgPool3d, StepModule

API Language: 中文 | English

中文
中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.AdaptiveAvgPool3d

English
English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.AdaptiveAvgPool3d for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.Linear(in_features: int, out_features: int, bias: bool = True, step_mode='s')[源代码]#

基类：Linear, StepModule

API Language: 中文 | English

中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.Linear

English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.Linear for other parameters' API

返回:: None
返回类型:: None

class spikingjelly.activation_based.layer.stateless_wrapper.Flatten(start_dim: int = 1, end_dim: int = -1, step_mode='s')[源代码]#

基类：Flatten, StepModule

API Language: 中文 | English

中文
中文

参数:: step_mode (str) -- 步进模式，可以为 's' (单步) 或 'm' (多步)

其他的参数API参见 torch.nn.Flatten

English
English

参数:: step_mode (str) -- the step mode, which can be s (single-step) or m (multi-step)

Refer to torch.nn.Flatten for other parameters' API

返回:: None
返回类型:: None

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.WSConv2d(in_channels: int, out_channels: int, kernel_size: int | tuple[int, int], stride: int | tuple[int, int] = 1, padding: str | int | tuple[int, int] = 0, dilation: int | tuple[int, int] = 1, groups: int = 1, bias: bool = True, padding_mode: str = 'zeros', step_mode: str = 's', gain: bool = True, eps: float = 0.0001)[源代码]#

基类：Conv2d

API Language: 中文 | English

中文

参数:

gain (bool) -- 是否对权重引入可学习的缩放系数
eps (float) -- 预防数值问题的小量

其他的参数API参见 Conv2d

English

参数:

gain -- whether introduce learnable scale factors for weights
eps (float) -- a small number to prevent numerical problems

Refer to Conv2d for other parameters' API

返回:: None
返回类型:: None

get_weight()[源代码]#

forward(x: Tensor)[源代码]#

class spikingjelly.activation_based.layer.stateless_wrapper.WSLinear(in_features: int, out_features: int, bias: bool = True, step_mode='s', gain=True, eps=0.0001)[源代码]#

基类：Linear

API Language: 中文 | English

中文

参数:

gain (bool) -- 是否对权重引入可学习的缩放系数
eps (float) -- 预防数值问题的小量

其他的参数API参见 Linear

English

参数:

gain -- whether introduce learnable scale factors for weights
eps (float) -- a small number to prevent numerical problems

Refer to Linear for other parameters' API

返回:: None
返回类型:: None

get_weight()[源代码]#

forward(x: Tensor)[源代码]#