spikingjelly.clock_driven.neuron package
Module contents
- class spikingjelly.clock_driven.neuron.BaseNode(v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False)[源代码]
基类：
MemoryModule- 参数
可微分SNN神经元的基类神经元。
- 参数
v_threshold (float) – threshold voltage of neurons
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
This class is the base class of differentiable spiking neurons.
- abstract neuronal_charge(x: Tensor)[源代码]
定义神经元的充电差分方程。子类必须实现这个函数。
Define the charge difference equation. The sub-class must implement this function.
- neuronal_fire()[源代码]
-
根据当前神经元的电压、阈值，计算输出脉冲。
Calculate out spikes of neurons by their current membrane potential and threshold voltage.
- neuronal_reset(spike)[源代码]
-
根据当前神经元释放的脉冲，对膜电位进行重置。
Reset the membrane potential according to neurons’ output spikes.
- forward(x: Tensor)[源代码]
-
- 参数
x (torch.Tensor) – 输入到神经元的电压增量
- 返回
神经元的输出脉冲
- 返回类型
按照充电、放电、重置的顺序进行前向传播。
- 参数
x (torch.Tensor) – increment of voltage inputted to neurons
- 返回
out spikes of neurons
- 返回类型
Forward by the order of neuronal_charge, neuronal_fire, and neuronal_reset.
- class spikingjelly.clock_driven.neuron.AdaptiveBaseNode(v_threshold: float = 1.0, v_reset: float = 0.0, v_rest: float = 0.0, w_rest: float = 0, tau_w: float = 2.0, a: float = 0.0, b: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False)[源代码]
基类：
BaseNode- forward(x: torch.Tensor)
Helper for @overload to raise when called.
- class spikingjelly.clock_driven.neuron.IFNode(v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False, cupy_fp32_inference=False)[源代码]
基类：
BaseNode- 参数
v_threshold (float) – 神经元的阈值电压
v_reset (float) – 神经元的重置电压。如果不为
None，当神经元释放脉冲后，电压会被重置为v_reset； 如果设置为None，则电压会被减去v_thresholdsurrogate_function (Callable) – 反向传播时用来计算脉冲函数梯度的替代函数
detach_reset (bool) – 是否将reset过程的计算图分离
cupy_fp32_inference (bool) – 若为 True，在 eval 模式下，使用float32，却在GPU上运行，并且 cupy 已经安装，则会自动使用 cupy 进行加速
Integrate-and-Fire 神经元模型，可以看作理想积分器，无输入时电压保持恒定，不会像LIF神经元那样衰减。其阈下神经动力学方程为：
\[V[t] = V[t-1] + X[t]\]- 参数
v_threshold (float) – threshold voltage of neurons
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
cupy_fp32_inference (bool) – If True, if this module is in eval mode, using float32, running on GPU, and cupy is installed, then this module will use cupy to accelerate
The Integrate-and-Fire neuron, which can be seen as a ideal integrator. The voltage of the IF neuron will not decay as that of the LIF neuron. The subthreshold neural dynamics of it is as followed:
\[V[t] = V[t-1] + X[t]\]
- class spikingjelly.clock_driven.neuron.MultiStepIFNode(v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False, backend='torch', lava_s_cale=64)[源代码]
基类：
IFNode- 参数
多步版本的
spikingjelly.clock_driven.neuron.IFNode。小技巧
对于多步神经元，输入
x_seq.shape = [T, *]，不仅可以使用.v和.spike获取t = T - 1时刻的电压和脉冲，还能够 使用.v_seq和.spike_seq获取完整的T个时刻的电压和脉冲。小技巧
阅读 传播模式 以获取更多关于单步和多步传播的信息。
- 参数
v_threshold (float) – threshold voltage of neurons
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
backend (str) – use which backend,
'torch'or'cupy'.'cupy'is faster but only supports GPU
The multi-step version of
spikingjelly.clock_driven.neuron.IFNode.Tip
The input for multi-step neurons are
x_seq.shape = [T, *]. We can get membrane potential and spike at time-stept = T - 1by.vand.spike. We can also get membrane potential and spike at allTtime-steps by.v_seqand.spike_seq.Tip
Read Propagation Pattern for more details about single-step and multi-step propagation.
- class spikingjelly.clock_driven.neuron.LIFNode(tau: float = 2.0, decay_input: bool = True, v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False, cupy_fp32_inference=False)[源代码]
基类：
BaseNode- 参数
tau (float) – 膜电位时间常数
decay_input (bool) – 输入是否会衰减
v_threshold (float) – 神经元的阈值电压
v_reset (float) – 神经元的重置电压。如果不为
None，当神经元释放脉冲后，电压会被重置为v_reset； 如果设置为None，则电压会被减去v_thresholdsurrogate_function (Callable) – 反向传播时用来计算脉冲函数梯度的替代函数
detach_reset (bool) – 是否将reset过程的计算图分离
cupy_fp32_inference (bool) – 若为 True，在 eval 模式下，使用float32，却在GPU上运行，并且 cupy 已经安装，则会自动使用 cupy 进行加速
Leaky Integrate-and-Fire 神经元模型，可以看作是带漏电的积分器。其阈下神经动力学方程为：
若
decay_input == True:\[V[t] = V[t-1] + \frac{1}{\tau}(X[t] - (V[t-1] - V_{reset}))\]若
decay_input == False:\[V[t] = V[t-1] - \frac{1}{\tau}(V[t-1] - V_{reset}) + X[t]\]小技巧
在 eval 模式下，使用float32，却在GPU上运行，并且 cupy 已经安装，则会自动使用 cupy 进行加速。
- 参数
tau (float) – membrane time constant
decay_input (bool) – whether the input will decay
v_threshold (float) – threshold voltage of neurons
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
cupy_fp32_inference (bool) – If True, if this module is in eval mode, using float32, running on GPU, and cupy is installed, then this module will use cupy to accelerate
The Leaky Integrate-and-Fire neuron, which can be seen as a leaky integrator. The subthreshold neural dynamics of it is as followed:
IF
decay_input == True:\[V[t] = V[t-1] + \frac{1}{\tau}(X[t] - (V[t-1] - V_{reset}))\]IF
decay_input == False:\[V[t] = V[t-1] - \frac{1}{\tau}(V[t-1] - V_{reset}) + X[t]\]Tip
If this module is in eval mode, using float32, running on GPU, and cupy is installed, then this module will use cupy to accelerate.
- class spikingjelly.clock_driven.neuron.MultiStepLIFNode(tau: float = 2.0, decay_input: bool = True, v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False, backend='torch', lava_s_cale=64)[源代码]
基类：
LIFNode- 参数
tau (float) – 膜电位时间常数
decay_input (bool) – 输入是否会衰减
v_threshold (float) – 神经元的阈值电压
v_reset (float) – 神经元的重置电压。如果不为
None，当神经元释放脉冲后，电压会被重置为v_reset； 如果设置为None，则电压会被减去v_thresholdsurrogate_function (Callable) – 反向传播时用来计算脉冲函数梯度的替代函数
detach_reset (bool) – 是否将reset过程的计算图分离
backend (str) – 使用哪种计算后端，可以为
'torch'或'cupy'。'cupy'速度更快，但仅支持GPU。
多步版本的
spikingjelly.clock_driven.neuron.LIFNode。小技巧
对于多步神经元，输入
x_seq.shape = [T, *]，不仅可以使用.v和.spike获取t = T - 1时刻的电压和脉冲，还能够 使用.v_seq和.spike_seq获取完整的T个时刻的电压和脉冲。小技巧
阅读 传播模式 以获取更多关于单步和多步传播的信息。
- 参数
tau (float) – membrane time constant
decay_input (bool) – whether the input will decay
v_threshold (float) – threshold voltage of neurons
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
backend (str) – use which backend,
'torch'or'cupy'.'cupy'is faster but only supports GPU
The multi-step version of
spikingjelly.clock_driven.neuron.LIFNode.Tip
The input for multi-step neurons are
x_seq.shape = [T, *]. We can get membrane potential and spike at time-stept = T - 1by.vand.spike. We can also get membrane potential and spike at allTtime-steps by.v_seqand.spike_seq.Tip
Read Propagation Pattern for more details about single-step and multi-step propagation.
- class spikingjelly.clock_driven.neuron.ParametricLIFNode(init_tau: float = 2.0, decay_input: bool = True, v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False)[源代码]
基类：
BaseNode- 参数
Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks 提出的 Parametric Leaky Integrate-and-Fire (PLIF)神经元模型，可以看作是带漏电的积分器。其阈下神经动力学方程为：
若
decay_input == True:\[V[t] = V[t-1] + \frac{1}{\tau}(X[t] - (V[t-1] - V_{reset}))\]若
decay_input == False:\[V[t] = V[t-1] - \frac{1}{\tau}(V[t-1] - V_{reset}) + X[t]\]其中 \(\frac{1}{\tau} = {\rm Sigmoid}(w)\)，\(w\) 是可学习的参数。
- 参数
init_tau (float) – the initial value of membrane time constant
decay_input (bool) – whether the input will decay
v_threshold (float) – threshold voltage of neurons
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
The Parametric Leaky Integrate-and-Fire (PLIF) neuron, which is proposed by Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks and can be seen as a leaky integrator. The subthreshold neural dynamics of it is as followed:
IF
decay_input == True:\[V[t] = V[t-1] + \frac{1}{\tau}(X[t] - (V[t-1] - V_{reset}))\]IF
decay_input == False:\[V[t] = V[t-1] - \frac{1}{\tau}(V[t-1] - V_{reset}) + X[t]\]where \(\frac{1}{\tau} = {\rm Sigmoid}(w)\), \(w\) is a learnable parameter.
- class spikingjelly.clock_driven.neuron.MultiStepParametricLIFNode(init_tau: float = 2.0, decay_input: bool = True, v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False, backend='torch')[源代码]
-
- 参数
多步版本的 Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks 提出的 Parametric Leaky Integrate-and-Fire (PLIF)神经元模型，可以看作是带漏电的积分器。其阈下神经动力学方程为：
\[V[t] = V[t-1] + \frac{1}{\tau}(X[t] - (V[t-1] - V_{reset})\]其中 \(\frac{1}{\tau} = {\rm Sigmoid}(w)\)，\(w\) 是可学习的参数。
小技巧
对于多步神经元，输入
x_seq.shape = [T, *]，不仅可以使用.v和.spike获取t = T - 1时刻的电压和脉冲，还能够 使用.v_seq和.spike_seq获取完整的T个时刻的电压和脉冲。小技巧
阅读 传播模式 以获取更多关于单步和多步传播的信息。
- 参数
init_tau (float) – the initial value of membrane time constant
decay_input (bool) – whether the input will decay
v_threshold (float) – threshold voltage of neurons
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
backend (str) – use which backend,
'torch'or'cupy'.'cupy'is faster but only supports GPU
The multi-step Parametric Leaky Integrate-and-Fire (PLIF) neuron, which is proposed by Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks and can be seen as a leaky integrator. The subthreshold neural dynamics of it is as followed:
\[V[t] = V[t-1] + \frac{1}{\tau}(X[t] - (V[t-1] - V_{reset})\]where \(\frac{1}{\tau} = {\rm Sigmoid}(w)\), \(w\) is a learnable parameter.
Tip
The input for multi-step neurons are
x_seq.shape = [T, *]. We can get membrane potential and spike at time-stept = T - 1by.vand.spike. We can also get membrane potential and spike at allTtime-steps by.v_seqand.spike_seq.Tip
Read Propagation Pattern for more details about single-step and multi-step propagation.
- class spikingjelly.clock_driven.neuron.QIFNode(tau: float = 2.0, v_c: float = 0.8, a0: float = 1.0, v_threshold: float = 1.0, v_rest: float = 0.0, v_reset: float = -0.1, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False)[源代码]
基类：
BaseNode- 参数
Quadratic Integrate-and-Fire 神经元模型，一种非线性积分发放神经元模型，也是指数积分发放神经元(Exponential Integrate-and-Fire)的近似版本。其阈下神经动力学方程为：
\[V[t] = V[t-1] + \frac{1}{\tau}(X[t] + a_0 (V[t-1] - V_{rest})(V[t-1] - V_c))\]- 参数
tau (float) – membrane time constant
v_c (float) – critical voltage
a0 (float) –
v_threshold (float) – threshold voltage of neurons
v_rest (float) – resting potential
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
The Quadratic Integrate-and-Fire neuron is a kind of nonlinear integrate-and-fire models and also an approximation of the Exponential Integrate-and-Fire model. The subthreshold neural dynamics of it is as followed:
\[V[t] = V[t-1] + \frac{1}{\tau}(X[t] + a_0 (V[t-1] - V_{rest})(V[t-1] - V_c))\]
- class spikingjelly.clock_driven.neuron.EIFNode(tau: float = 2.0, delta_T: float = 1.0, theta_rh: float = 0.8, v_threshold: float = 1.0, v_rest: float = 0.0, v_reset: float = -0.1, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False)[源代码]
基类：
BaseNode- 参数
tau (float) – 膜电位时间常数
delta_T (float) – 陡峭度参数
theta_rh (float) – 基强度电压阈值
v_threshold (float) – 神经元的阈值电压
v_rest (float) – 静息电位
v_reset (float) – 神经元的重置电压。如果不为
None，当神经元释放脉冲后，电压会被重置为v_reset； 如果设置为None，则电压会被减去v_thresholdsurrogate_function (Callable) – 反向传播时用来计算脉冲函数梯度的替代函数
detach_reset (bool) – 是否将reset过程的计算图分离
Exponential Integrate-and-Fire 神经元模型，一种非线性积分发放神经元模型，是由HH神经元模型(Hodgkin-Huxley model)简化后推导出的一维模型。在 \(\Delta_T\to 0\) 时退化为LIF模型。其阈下神经动力学方程为：
\[V[t] = V[t-1] + \frac{1}{\tau}\left(X[t] - (V[t-1] - V_{rest}) + \Delta_T\exp\left(\frac{V[t-1] - \theta_{rh}}{\Delta_T}\right)\right)\]- 参数
tau (float) – membrane time constant
delta_T (float) – sharpness parameter
theta_rh (float) – rheobase threshold
v_threshold (float) – threshold voltage of neurons
v_rest (float) – resting potential
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
The Exponential Integrate-and-Fire neuron is a kind of nonlinear integrate-and-fire models and also an one-dimensional model derived from the Hodgkin-Huxley model. It degenerates to the LIF model when \(\Delta_T\to 0\). The subthreshold neural dynamics of it is as followed:
\[V[t] = V[t-1] + \frac{1}{\tau}\left(X[t] - (V[t-1] - V_{rest}) + \Delta_T\exp\left(\frac{V[t-1] - \theta_{rh}}{\Delta_T}\right)\right)\]
- class spikingjelly.clock_driven.neuron.MultiStepEIFNode(tau: float = 2.0, delta_T: float = 1.0, theta_rh: float = 0.8, v_threshold: float = 1.0, v_rest: float = 0.0, v_reset: float = -0.1, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False, backend='torch')[源代码]
基类：
EIFNode::param tau: 膜电位时间常数 :type tau: float
- 参数
多步版本的
spikingjelly.clock_driven.neuron.EIFNode。对于多步神经元，输入
x_seq.shape = [T, *]，不仅可以使用.v和.spike获取t = T - 1时刻的电压和脉冲，还能够 使用.v_seq和.spike_seq获取完整的T个时刻的电压和脉冲。小技巧
阅读 传播模式 以获取更多关于单步和多步传播的信息。
- 参数
tau (float) – membrane time constant
delta_T (float) – sharpness parameter
theta_rh (float) – rheobase threshold
v_threshold (float) – threshold voltage of neurons
v_rest (float) – resting potential
v_reset (float) – reset voltage of neurons. If not
None, voltage of neurons that just fired spikes will be set tov_reset. IfNone, voltage of neurons that just fired spikes will subtractv_thresholdsurrogate_function (Callable) – surrogate function for replacing gradient of spiking functions during back-propagation
detach_reset (bool) – whether detach the computation graph of reset
backend (str) – use which backend,
'torch'or'cupy'.'cupy'is faster but only supports GPU
Tip
The input for multi-step neurons are
x_seq.shape = [T, *]. We can get membrane potential and spike at time-stept = T - 1by.vand.spike. We can also get membrane potential and spike at allTtime-steps by.v_seqand.spike_seq.Tip
Read Propagation Pattern for more details about single-step and multi-step propagation.
- class spikingjelly.clock_driven.neuron.GeneralNode(a: float, b: float, c: float = 0.0, v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False)[源代码]
基类：
BaseNode
- class spikingjelly.clock_driven.neuron.MultiStepGeneralNode(a: float, b: float, c: float, v_threshold: float = 1.0, v_reset: float = 0.0, surrogate_function: Callable = Sigmoid(alpha=4.0, spiking=True), detach_reset: bool = False, backend='torch')[源代码]
基类：
GeneralNode
- class spikingjelly.clock_driven.neuron.LIAFNode(act: Callable, threshold_related: bool, *args, **kwargs)[源代码]
基类：
LIFNode- 参数
act (Callable) – the activation function
threshold_related (bool) – whether the neuron uses threshold related (TR mode). If true, y = act(h - v_th), otherwise y = act(h)
Other parameters in *args, **kwargs are same with
LIFNode.The LIAF neuron proposed in LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing.
Warning
The outputs of this neuron are not binary spikes.