spikingjelly.clock_driven.ann2snn package

Subpackages

Submodules

spikingjelly.clock_driven.ann2snn.modules module

class spikingjelly.clock_driven.ann2snn.modules.MaxPool2d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False, momentum=None)[源代码]

基类：torch.nn.modules.module.Module

参数

  • kernel_size – 窗口取最大的大小

  • stride – 窗口的步长. 默认值为 kernel_size

  • padding – 隐式两侧填充零的大小

  • dilation – 控制窗口中元素的步幅的参数

  • return_indices – 当 True ，将返回最大序号并输出

  • ceil_mode – 当 True ，将使用 ceil 而不是 floor 来计算输出形状

  • momentum – 当在[0，1]中，将在门控函数中使用在线动量统计; 当为 None 时，将在门控函数中使用累计脉冲数

返回

None

基于文献 1 中2.2.6章节设计MaxPool2d模块。为了兼容Pytorch的MaxPool2d模块，众多参数设定和Pytorch相同。详情请见 torch.nn.MaxPool2d 。 基本想法是对输入脉冲进行统计，统计量可以控制门控函数确定以哪一路输入信号作为输出。 根据 momentum 参数类型不同可以有不同的统计功能。 momentum 参数支持None值和[0,1]区间的浮点数数值作为输出。 假定在t时刻，脉冲输入张量为 \(s_t\) ，脉冲统计量为 \(p_t\) 当 momentum 参数为 None 时，统计量为累计脉冲数

\[p_t = p_{t-1} + s_t\]

当 momentum 参数为[0,1]区间的浮点数时，统计量为在线的动量累积

\[p_t = momentum * p_{t-1} + (1-momentum) * s_t\]
参数

  • kernel_size – the size of the window to take a max over

  • stride – the stride of the window. Default value is kernel_size

  • padding – implicit zero padding to be added on both sides

  • dilation – a parameter that controls the stride of elements in the window

  • return_indices – if True, will return the max indices along with the outputs. Useful for torch.nn.MaxUnpool2d later

  • ceil_mode – when True, will use ceil instead of floor to compute the output shape

  • momentum – when in [0,1], will use online momentum statistics in gate functions; when None, will use accumulated spike in gate functions

返回

None

Design the MaxPool2d module based on section 2.2.6 in 1 . In order to be compatible with Pytorch’s MaxPool2d module, many parameter settings are the same as Pytorch. See torch.nn.MaxPool2d for details. The basic idea is to accumulate the input spikes, which can control the gating function to determine which input spike is used as output. Depending on the type of momentum parameter, different statistical functions can be used. momentum supports the floating-point value in [0,1] or value None Assume at time t, the spike input is \(s_t\) and the spike statistic is \(p_t\). When momentum is None, the statistic is sum of spikes over time.

\[p_t = p_{t-1} + s_t\]

When momentum is a floating point in [0,1], the statistic is online momentum of spikes.

\[p_t = momentum * p_{t-1} + (1-momentum) * s_t\]
1(1,2)

Rueckauer B, Lungu I-A, Hu Y, Pfeiffer M and Liu S-C (2017) Conversion of Continuous-Valued Deep Networks to

Efficient Event-Driven Networks for Image Classification. Front. Neurosci. 11:682.

forward(dv: torch.Tensor)[源代码]
reset()[源代码]
返回

None

重置神经元为初始状态

training: bool
class spikingjelly.clock_driven.ann2snn.modules.AccuLayer(momentum=None)[源代码]

基类：torch.nn.modules.module.Module

forward(spk: torch.Tensor)[源代码]
reset()[源代码]
返回

None

重置神经元为初始状态

training: bool

Module contents

class spikingjelly.clock_driven.ann2snn.parser(name='', kernel='onnx', **kargs)[源代码]

基类：object

parse(model: torch.nn.modules.module.Module, data: torch.Tensor, **kargs) → torch.nn.modules.module.Module[源代码]
to_snn(model: torch.nn.modules.module.Module, **kargs) → torch.nn.modules.module.Module[源代码]
spikingjelly.clock_driven.ann2snn.z_norm_integration(model: torch.nn.modules.module.Module, z_norm=None) → torch.nn.modules.module.Module[源代码]
class spikingjelly.clock_driven.ann2snn.simulator(snn, device, name='', **kargs)[源代码]

基类：object

simulate(data_loader, T, **kargs)[源代码]
get_values(data, targets, device, T, func_dict, **kargs)[源代码]
class spikingjelly.clock_driven.ann2snn.classify_simulator(snn, device, **kargs)[源代码]

基类：spikingjelly.clock_driven.ann2snn.simulator

static correct_num(targets, out_spike_cnt, **kargs) → float[源代码]
static total_num(targets, **kargs) → float[源代码]