spikingjelly.cext.neuron package

Module contents

spikingjelly.cext.neuron.hard_reset_forward_template(x: torch.Tensor, v: torch.Tensor, v_threshold: float, v_reset: float, *args, **kwargs)

• API in English

参数

• x (torch.Tensor) – \(X_{t}\)

• v (torch.Tensor) – \(V_{t-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

返回

(spike, v_next)，其中 spike 是 \(S_{t}\)，v_next 是 \(V_{t}\)

返回类型

tuple

对神经元进行单步的电压更新，其中电压重置方式是硬重置(hard reset)。更新的方程为

\[ \begin{align}\begin{aligned}H_{t} & = f(X_{t}, V_{t-1}; \theta)\\S_{t} & = \Theta(H_{t} - V_{threshold})\\V_{t} & = S_{t}V_{reset} + (1 - S_{t})H_{t}\end{aligned}\end{align} \]

其中 \(f(\cdot)\) 是充电方程，\(\theta\) 是神经元自身的参数。

• 中文API

参数

• x (torch.Tensor) – \(X_{t}\)

• v (torch.Tensor) – \(V_{t-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

返回

(spike, v_next), where spike is \(S_{t}\), and v_next is \(V_{t}\)

返回类型

tuple

Update the membrane potential of the neuron by one time step with hard reset. The update is calculated by

\[ \begin{align}\begin{aligned}H_{t} & = f(X_{t}, V_{t-1}; \theta)\\S_{t} & = \Theta(H_{t} - V_{threshold})\\V_{t} & = S_{t}V_{reset} + (1 - S_{t})H_{t}\end{aligned}\end{align} \]

where \(f(\cdot)\) is the charging equation and \(\theta\) is the neuron’s parameters.

spikingjelly.cext.neuron.hard_reset_fptt_template(x_seq: torch.Tensor, v: torch.Tensor, v_threshold: float, v_reset: float, *args, **kwargs)

• API in English

参数

• x (torch.Tensor) – \(X_{t}, t=0,1,...,T-1\)

• v (torch.Tensor) – \(V_{-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

返回

(spike_seq, v_next)，其中 spike 是 \(S_{t}, t=0,1,...,T-1\)，v_next 是 \(V_{T-1}\)

返回类型

tuple

hard_reset_forward_template 的多步版本。

• 中文API

参数

• x (torch.Tensor) – \(X_{t}, t=0,1,...,T-1\)

• v (torch.Tensor) – \(V_{-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

返回

(spike_seq, v_next), where spike is \(S_{t}, t=0,1,...,T-1\), v_next is \(V_{T-1}\)

返回类型

tuple

The multi-step version of hard_reset_forward_template.

spikingjelly.cext.neuron.soft_reset_forward_template(x: torch.Tensor, v: torch.Tensor, v_threshold: float, *args, **kwargs)

• API in English

参数

• x (torch.Tensor) – \(X_{t}\)

• v (torch.Tensor) – \(V_{t-1}\)

• v_threshold (float) – \(V_{threshold}\)

返回

(spike, v_next)，其中 spike 是 \(S_{t}\)，v_next 是 \(V_{t}\)

返回类型

tuple

对神经元进行单步的电压更新，其中电压重置方式是软重置(soft reset)。更新的方程为

\[ \begin{align}\begin{aligned}H_{t} & = f(X_{t}, V_{t-1}; \theta)\\S_{t} & = \Theta(H_{t} - V_{threshold})\\V_{t} & = H_{t} - S_{t}V_{threshold}\end{aligned}\end{align} \]

其中 \(f(\cdot)\) 是充电方程，\(\theta\) 是神经元自身的参数。

• 中文API

参数

• x (torch.Tensor) – \(X_{t}\)

• v (torch.Tensor) – \(V_{t-1}\)

• v_threshold (float) – \(V_{threshold}\)

返回

(spike, v_next), where spike is \(S_{t}\), and v_next is \(V_{t}\)

返回类型

tuple

Update the membrane potential of the neuron by one time step with soft reset. The update is calculated by

\[ \begin{align}\begin{aligned}H_{t} & = f(X_{t}, V_{t-1}; \theta)\\S_{t} & = \Theta(H_{t} - V_{threshold})\\V_{t} & = H_{t} - S_{t}V_{threshold}\end{aligned}\end{align} \]

where \(f(\cdot)\) is the charging equation and \(\theta\) is the neuron’s parameters.

spikingjelly.cext.neuron.soft_reset_fptt_template(x_seq: torch.Tensor, v: torch.Tensor, v_threshold: float, *args, **kwargs)

• API in English

参数

• x (torch.Tensor) – \(X_{t}, t=0,1,...,T-1\)

• v (torch.Tensor) – \(V_{-1}\)

• v_threshold (float) – \(V_{threshold}\)

返回

(spike_seq, v_next)，其中 spike 是 \(S_{t}, t=0,1,...,T-1\)，v_next 是 \(V_{T-1}\)

返回类型

tuple

soft_reset_forward_template 的多步版本。

• 中文API

参数

• x (torch.Tensor) – \(X_{t}, t=0,1,...,T-1\)

• v (torch.Tensor) – \(V_{-1}\)

• v_threshold (float) – \(V_{threshold}\)

返回

(spike_seq, v_next), where spike is \(S_{t}, t=0,1,...,T-1\), v_next is \(V_{T-1}\)

返回类型

tuple

The multi-step version of soft_reset_forward_template.

spikingjelly.cext.neuron.hard_reset_forward_with_grad_template(x: torch.Tensor, v: torch.Tensor, v_threshold: float, v_reset: float, alpha: float, detach_reset: bool, grad_surrogate_function_index: int, *args, **kwargs)

• API in English

参数

• x (torch.Tensor) – \(X_{t}\)

• v (torch.Tensor) – \(V_{t-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

• alpha (float) – \(\alpha\)

• detach_reset (bool) – 是否在反向传播的计算图中断开重置过程

• grad_surrogate_function_index (int) – 梯度替代函数的索引

返回

(spike, v_next, grad_s_to_h, grad_v_to_h)，其中 spike 是 \(S_{t}\)，v_next 是 \(V_{t}\)，grad_s_to_h 是 \(\frac{\partial S_{t}}{\partial H_{t}}\)，grad_v_to_h 是 \(\frac{\partial V_{t}}{\partial H_{t}}\)

返回类型

tuple

对神经元进行单步的电压更新，其中电压重置方式是硬重置(hard reset)。更新的方程为

\[ \begin{align}\begin{aligned}H_{t} & = f(X_{t}, V_{t-1}; \theta)\\S_{t} & = \Theta(H_{t} - V_{threshold})\\V_{t} & = S_{t}V_{reset} + (1 - S_{t})H_{t}\end{aligned}\end{align} \]

其中 \(f(\cdot)\) 是充电方程，\(\theta\) 是神经元自身的参数。并且会计算出反向传播所需的梯度

\[ \begin{align}\begin{aligned}\frac{\partial S_{t}}{\partial H_{t}} & = \Theta'(H_{t} - V_{threshold}) = \sigma(\alpha(H_{t} - V_{threshold}))\\\frac{\partial V_{t}}{\partial H_{t}} & = 1 - S_{t} + (V_{reset} - H_{t})\frac{\partial S_{t}}{\partial H_{t}}\end{aligned}\end{align} \]

• 中文API

参数

• x (torch.Tensor) – \(X_{t}\)

• v (torch.Tensor) – \(V_{t-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

• alpha (float) – \(\alpha\)

• detach_reset (bool) – whether detach the neuronal reset during backward

• grad_surrogate_function_index (int) – index of the gradient surrogate function

返回

(spike, v_next, grad_s_to_h, grad_v_to_h), where spike is \(S_{t}\), v_next is \(V_{t}\), grad_s_to_h is \(\frac{\partial S_{t}}{\partial H_{t}}\), grad_v_to_h is \(\frac{\partial V_{t}}{\partial H_{t}}\)

返回类型

tuple

Update the membrane potential of the neuron by one time step with hard reset. The update is calculated by

\[ \begin{align}\begin{aligned}H_{t} & = f(X_{t}, V_{t-1}; \theta)\\S_{t} & = \Theta(H_{t} - V_{threshold})\\V_{t} & = S_{t}V_{reset} + (1 - S_{t})H_{t}\end{aligned}\end{align} \]

where \(f(\cdot)\) is the charging equation and \(\theta\) is the neuron’s parameters. This function will also calculate the gradients which the backward function needs

\[ \begin{align}\begin{aligned}\frac{\partial S_{t}}{\partial H_{t}} & = \Theta'(H_{t} - V_{threshold}) = \sigma(\alpha(H_{t} - V_{threshold}))\\\frac{\partial V_{t}}{\partial H_{t}} & = 1 - S_{t} + (V_{reset} - H_{t})\frac{\partial S_{t}}{\partial H_{t}}\end{aligned}\end{align} \]

spikingjelly.cext.neuron.hard_reset_fptt_with_grad_template(x_seq: torch.Tensor, v: torch.Tensor, v_threshold: float, v_reset: float, alpha: float, detach_reset: bool, grad_surrogate_function_index: int, *args, **kwargs)

• API in English

参数

• x_seq – \(X_{t}, t=0,1,...,T-1\)

• v (torch.Tensor) – \(V_{-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

• alpha (float) – \(\alpha\)

• detach_reset (bool) – 是否在反向传播的计算图中断开重置过程

• grad_surrogate_function_index (int) – 梯度替代函数的索引

返回

(spike_seq, v_next, grad_s_to_h, grad_v_to_h)，其中 spike_seq 是 \(S_{t}, t=0,1,...,T-1\)，v_next 是 \(V_{T-1}\)，grad_s_to_h 是 \(\frac{\partial S_{t}}{\partial H_{t}}, t=0,1,...,T-1\)，grad_v_to_h 是 \(\frac{\partial V_{t}}{\partial H_{t}}, t=0,1,...,T-1\)

返回类型

tuple

hard_reset_forward_with_grad_template 的多步版本。

• 中文API

参数

• x_seq – \(X_{t}, t=0,1,...,T-1\)

• v (torch.Tensor) – \(V_{-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

• alpha (float) – \(\alpha\)

• detach_reset (bool) – whether detach the neuronal reset during backward

• grad_surrogate_function_index (int) – index of the gradient surrogate function

返回

(spike_seq, v_next, grad_s_to_h, grad_v_to_h), where spike_seq is \(S_{t}, t=0,1,...,T-1\), v_next is \(V_{T-1}\), grad_s_to_h is \(\frac{\partial S_{t}}{\partial H_{t}}, t=0,1,...,T-1\), grad_v_to_h is \(\frac{\partial V_{t}}{\partial H_{t}}, t=0,1,...,T-1\)

返回类型

tuple

The multi-step version of hard_reset_forward_with_grad_template.

spikingjelly.cext.neuron.soft_reset_forward_with_grad_template(x: torch.Tensor, v: torch.Tensor, v_threshold: float, alpha: float, detach_reset: bool, grad_surrogate_function_index: int, *args, **kwargs)

• API in English

参数

• x (torch.Tensor) – \(X_{t}\)

• v (torch.Tensor) – \(V_{t-1}\)

• v_threshold (float) – \(V_{threshold}\)

• alpha (float) – \(\alpha\)

• detach_reset (bool) – 是否在反向传播的计算图中断开重置过程

• grad_surrogate_function_index (int) – 梯度替代函数的索引

返回

(spike, v_next, grad_s_to_h, grad_v_to_h)，其中 spike 是 \(S_{t}\)，v_next 是 \(V_{t}\)，grad_s_to_h 是 \(\frac{\partial S_{t}}{\partial H_{t}}\)，grad_v_to_h 是 \(\frac{\partial V_{t}}{\partial H_{t}}\)

返回类型

tuple

对神经元进行单步的电压更新，其中电压重置方式是软重置(soft reset)。更新的方程为

\[ \begin{align}\begin{aligned}H_{t} & = f(X_{t}, V_{t-1}; \theta)\\S_{t} & = \Theta(H_{t} - V_{threshold})\\V_{t} & = H_{t} - S_{t}V_{threshold}\end{aligned}\end{align} \]

其中 \(f(\cdot)\) 是充电方程，\(\theta\) 是神经元自身的参数。并且会计算出反向传播所需的梯度

\[ \begin{align}\begin{aligned}\frac{\partial S_{t}}{\partial H_{t}} & = \Theta'(H_{t} - V_{threshold}) = \sigma(\alpha(H_{t} - V_{threshold}))\\\frac{\partial V_{t}}{\partial H_{t}} & = 1 - V_{threshold} \frac{\partial S_{t}}{\partial H_{t}}\end{aligned}\end{align} \]

• 中文API

参数

• x (torch.Tensor) – \(X_{t}\)

• v (torch.Tensor) – \(V_{t-1}\)

• v_threshold (float) – \(V_{threshold}\)

• alpha (float) – \(\alpha\)

• detach_reset (bool) – whether detach the neuronal reset during backward

• grad_surrogate_function_index (int) – index of the gradient surrogate function

返回

(spike, v_next, grad_s_to_h, grad_v_to_h), where spike is \(S_{t}\), v_next is \(V_{t}\), grad_s_to_h is \(\frac{\partial S_{t}}{\partial H_{t}}\), grad_v_to_h is \(\frac{\partial V_{t}}{\partial H_{t}}\)

返回类型

tuple

Update the membrane potential of the neuron by one time step with soft reset. The update is calculated by

\[ \begin{align}\begin{aligned}H_{t} & = f(X_{t}, V_{t-1}; \theta)\\S_{t} & = \Theta(H_{t} - V_{threshold})\\V_{t} & = H_{t} - S_{t}V_{threshold}\end{aligned}\end{align} \]

where \(f(\cdot)\) is the charging equation and \(\theta\) is the neuron’s parameters. This function will also calculate the gradients which the backward function needs

\[ \begin{align}\begin{aligned}\frac{\partial S_{t}}{\partial H_{t}} & = \Theta'(H_{t} - V_{threshold}) = \sigma(\alpha(H_{t} - V_{threshold}))\\\frac{\partial V_{t}}{\partial H_{t}} & = 1 - V_{threshold} \frac{\partial S_{t}}{\partial H_{t}}\end{aligned}\end{align} \]

spikingjelly.cext.neuron.soft_reset_fptt_with_grad_template(x_seq: torch.Tensor, v: torch.Tensor, v_threshold: float, alpha: float, detach_reset: bool, grad_surrogate_function_index: int, *args, **kwargs)

• API in English

参数

• x_seq – \(X_{t}, t=0,1,...,T-1\)

• v (torch.Tensor) – \(V_{-1}\)

• v_threshold (float) – \(V_{threshold}\)

• alpha (float) – \(\alpha\)

• detach_reset (bool) – 是否在反向传播的计算图中断开重置过程

• grad_surrogate_function_index (int) – 梯度替代函数的索引

返回

(spike_seq, v_next, grad_s_to_h, grad_v_to_h)，其中 spike_seq 是 \(S_{t}, t=0,1,...,T-1\)，v_next 是 \(V_{T-1}\)，grad_s_to_h 是 \(\frac{\partial S_{t}}{\partial H_{t}}, t=0,1,...,T-1\)，grad_v_to_h 是 \(\frac{\partial V_{t}}{\partial H_{t}}, t=0,1,...,T-1\)

返回类型

tuple

soft_reset_forward_with_grad_template 的多步版本。

• 中文API

参数

• x_seq – \(X_{t}, t=0,1,...,T-1\)

• v (torch.Tensor) – \(V_{-1}\)

• v_threshold (float) – \(V_{threshold}\)

• v_reset (float) – \(V_{reset}\)

• alpha (float) – \(\alpha\)

• detach_reset (bool) – whether detach the neuronal reset during backward

• grad_surrogate_function_index (int) – index of the gradient surrogate function

返回

(spike_seq, v_next, grad_s_to_h, grad_v_to_h), where spike_seq is \(S_{t}, t=0,1,...,T-1\), v_next is \(V_{T-1}\), grad_s_to_h is \(\frac{\partial S_{t}}{\partial H_{t}}, t=0,1,...,T-1\), grad_v_to_h is \(\frac{\partial V_{t}}{\partial H_{t}}, t=0,1,...,T-1\)

返回类型

tuple

The multi-step version of soft_reset_forward_with_grad_template.

spikingjelly.cext.neuron.backward_template(grad_spike: torch.Tensor, grad_v_next: torch.Tensor, grad_s_to_h: torch.Tensor, grad_v_to_h: float, *args, **kwargs)

• API in English

参数

• grad_spike (torch.Tensor) – \(\frac{\partial L}{\partial S_{t}}\)

• grad_v_next (torch.Tensor) – \(\frac{\partial L}{\partial V_{t}}\)

• grad_s_to_h (torch.Tensor) – \(\frac{\partial S_{t}}{\partial H_{t}}\)

• grad_v_to_h (torch.Tensor) – \(\frac{\partial V_{t}}{\partial H_{t}}\)

返回

(grad_x, grad_v)，其中 grad_x 是 \(\frac{\partial L}{\partial X_{t}}\)，grad_v 是 \(\frac{\partial L}{\partial V_{t-1}}\)

返回类型

tuple

hard_reset_forward_with_grad_template 和 soft_reset_forward_with_grad_template 的反向传播。梯度的计算按照

\[ \begin{align}\begin{aligned}\frac{\partial L}{\partial H_{t}} & = \frac{\partial L}{\partial S_{t}} \frac{\partial S_{t}}{\partial H_{t}} + \frac{\partial L}{\partial V_{t}} \frac{\partial V_{t}}{\partial H_{t}}\\\frac{\partial L}{\partial X_{t}} &= \frac{\partial L}{\partial H_{t}} \frac{\partial H_{t}}{\partial X_{t}}\\\frac{\partial L}{\partial V_{t-1}} &= \frac{\partial L}{\partial H_{t}} \frac{\partial H_{t}}{\partial V_{t-1}}\end{aligned}\end{align} \]

• 中文API

参数

• grad_spike (torch.Tensor) – \(\frac{\partial L}{\partial S_{t}}\)

• grad_v_next (torch.Tensor) – \(\frac{\partial L}{\partial V_{t}}\)

• grad_s_to_h (torch.Tensor) – \(\frac{\partial S_{t}}{\partial H_{t}}\)

• grad_v_to_h (torch.Tensor) – \(\frac{\partial V_{t}}{\partial H_{t}}\)

返回

(grad_x, grad_v), where grad_x is \(\frac{\partial L}{\partial X_{t}}\), grad_v is \(\frac{\partial L}{\partial V_{t-1}}\)

返回类型

tuple

The backward of hard_reset_forward_with_grad_template and soft_reset_forward_with_grad_template. The gradients are calculated by

\[ \begin{align}\begin{aligned}\frac{\partial L}{\partial H_{t}} & = \frac{\partial L}{\partial S_{t}} \frac{\partial S_{t}}{\partial H_{t}} + \frac{\partial L}{\partial V_{t}} \frac{\partial V_{t}}{\partial H_{t}}\\\frac{\partial L}{\partial X_{t}} &= \frac{\partial L}{\partial H_{t}} \frac{\partial H_{t}}{\partial X_{t}}\\\frac{\partial L}{\partial V_{t-1}} &= \frac{\partial L}{\partial H_{t}} \frac{\partial H_{t}}{\partial V_{t-1}}\end{aligned}\end{align} \]

spikingjelly.cext.neuron.bptt_template(grad_spike_seq: torch.Tensor, grad_v_next: torch.Tensor, grad_s_to_h: torch.Tensor, grad_v_to_h: torch.Tensor, *args, **kwargs)

• API in English

参数

• grad_spike_seq (torch.Tensor) – \(\frac{\partial L}{\partial S_{t}}, t=0,1,...,T-1\)

• grad_v_next (torch.Tensor) – \(\frac{\partial L}{\partial V_{T-1}}\)

• grad_s_to_h (torch.Tensor) – \(\frac{\partial S_{t}}{\partial H_{t}}, t=0,1,...,T-1\)

• grad_v_to_h (torch.Tensor) – \(\frac{\partial V_{t}}{\partial H_{t}}, t=0,1,...,T-1\)

返回

(grad_x_seq, grad_v)，其中 grad_x_seq 是 \(\frac{\partial L}{\partial X_{t}}, t=0,1,...,T-1\)，grad_v 是 \(\frac{\partial L}{\partial V_{-1}}\)

返回类型

tuple

backward_template 的多步版本。

• 中文API

参数

• grad_spike_seq (torch.Tensor) – \(\frac{\partial L}{\partial S_{t}}, t=0,1,...,T-1\)

• grad_v_next (torch.Tensor) – \(\frac{\partial L}{\partial V_{T-1}}\)

• grad_s_to_h (torch.Tensor) – \(\frac{\partial S_{t}}{\partial H_{t}}, t=0,1,...,T-1\)

• grad_v_to_h (torch.Tensor) – \(\frac{\partial V_{t}}{\partial H_{t}}, t=0,1,...,T-1\)

返回

(grad_x_seq, grad_v), where grad_x_seq is \(\frac{\partial L}{\partial X_{t}}, t=0,1,...,T-1\), grad_v is \(\frac{\partial L}{\partial V_{-1}}\)

返回类型

tuple

The multi-step version of backward_template.

spikingjelly.cext.neuron.LIF_hard_reset_forward(x: torch.Tensor, v: torch.Tensor, v_threshold: float, v_reset: float, reciprocal_tau: float, detach_input: bool)

• API in English

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

其余的参数参见 hard_reset_forward_template。

对LIF神经元进行单步的电压更新，其中电压重置方式是硬重置(hard reset)。充电的方程为

\[H_{t} = V_{t-1} + \frac{1}{\tau}(X_{t} -(V_{t-1} - V_{reset}))\]

• 中文API

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

See hard_reset_forward_template for more details about other args。

Update the membrane potential of the LIF neuron by one time step with hard reset. The charging equation is

\[H_{t} = V_{t-1} + \frac{1}{\tau}(X_{t} -(V_{t-1} - V_{reset}))\]

spikingjelly.cext.neuron.LIF_hard_reset_fptt(x_seq: torch.Tensor, v: torch.Tensor, v_threshold: float, v_reset: float, reciprocal_tau: float, detach_input: bool)

• API in English

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

其余的参数参见 hard_reset_fptt_template。

LIF_hard_reset_forward 的多步版本。

• 中文API

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

See hard_reset_fptt_template for more details about other args。

The multi-step version of LIF_hard_reset_forward.

spikingjelly.cext.neuron.LIF_hard_reset_forward_with_grad(x: torch.Tensor, v: torch.Tensor, v_threshold: float, v_reset: float, alpha: float, detach_reset: bool, grad_surrogate_function_index: int, reciprocal_tau: float, detach_input: bool)

• API in English

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

其余的参数参见 hard_reset_forward_with_grad_template。

对LIF神经元进行单步的电压更新并计算反向传播所需的梯度，其中电压重置方式是硬重置(hard reset)。充电的方程为

\[H_{t} = V_{t-1} + \frac{1}{\tau}(X_{t} -(V_{t-1} - V_{reset}))\]

• 中文API

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

See hard_reset_forward_with_grad_template for more details about other args。

Update the membrane potential of the LIF neuron by one time step with hard reset and calculate the gradients that the backward function needs. The charging equation is

\[H_{t} = V_{t-1} + \frac{1}{\tau}(X_{t} -(V_{t-1} - V_{reset}))\]

spikingjelly.cext.neuron.LIF_hard_reset_fptt_with_grad(x_seq: torch.Tensor, v: torch.Tensor, v_threshold: float, v_reset: float, alpha: float, detach_reset: bool, grad_surrogate_function_index: int, reciprocal_tau: float, detach_input: bool)

• API in English

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

其余的参数参见 hard_reset_fptt_with_grad_template。

LIF_hard_reset_forward_with_grad 的多步版本。

• 中文API

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

See hard_reset_fptt_with_grad_template for more details about other args。

The multi-step version of LIF_hard_reset_forward_with_grad.

spikingjelly.cext.neuron.LIF_backward(grad_spike: torch.Tensor, grad_v_next: torch.Tensor, grad_s_to_h: torch.Tensor, grad_v_to_h: float, reciprocal_tau: float, detach_input: bool)

• API in English

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

其余的参数参见 backward_template。

梯度的计算按照

\[ \begin{align}\begin{aligned}\frac{\partial H_{t}}{\partial X_{t}} & = \frac{1}{\tau}\\\frac{\partial H_{t}}{\partial V_{t-1}} & = 1 - \frac{1}{\tau}\end{aligned}\end{align} \]

• 中文API

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

See backward_template for more details about other args。

The gradients are calculated by

\[ \begin{align}\begin{aligned}\frac{\partial H_{t}}{\partial X_{t}} & = \frac{1}{\tau}\\\frac{\partial H_{t}}{\partial V_{t-1}} & = 1 - \frac{1}{\tau}\end{aligned}\end{align} \]

spikingjelly.cext.neuron.LIF_bptt(grad_spike: torch.Tensor, grad_v_next: torch.Tensor, grad_s_to_h: torch.Tensor, grad_v_to_h: float, reciprocal_tau: float, detach_input: bool)

• API in English

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

其余的参数参见 bptt_template。

LIF_backward 的多步版本。

梯度的计算按照

\[ \begin{align}\begin{aligned}\frac{\partial H_{t}}{\partial X_{t}} & = \frac{1}{\tau}\\\frac{\partial H_{t}}{\partial V_{t-1}} & = 1 - \frac{1}{\tau}\end{aligned}\end{align} \]

• 中文API

参数

reciprocal_tau (float) – \(\frac{1}{\tau}\)

See bptt_template for more details about other args。

The multi-step version of LIF_backward.

The gradients are calculated by

\[ \begin{align}\begin{aligned}\frac{\partial H_{t}}{\partial X_{t}} & = \frac{1}{\tau}\\\frac{\partial H_{t}}{\partial V_{t-1}} & = 1 - \frac{1}{\tau}\end{aligned}\end{align} \]

class spikingjelly.cext.neuron.LIFStep

基类：torch.autograd.function.Function

static forward(ctx, x, v, v_threshold, v_reset, alpha, detach_reset, grad_surrogate_function_index, reciprocal_tau, detach_input)

static backward(ctx, grad_spike, grad_v_next)

class spikingjelly.cext.neuron.LIFMultiStep

基类：torch.autograd.function.Function

static forward(ctx, x_seq, v, v_threshold, v_reset, alpha, detach_reset, grad_surrogate_function_index, reciprocal_tau, detach_input)

static backward(ctx, grad_spike_seq, grad_v_next)

class spikingjelly.cext.neuron.IFStep

基类：torch.autograd.function.Function

static forward(ctx, x, v, v_threshold, v_reset, alpha, detach_reset, grad_surrogate_function_index)

static backward(ctx, grad_spike, grad_v_next)

class spikingjelly.cext.neuron.IFMultiStep

基类：torch.autograd.function.Function

static forward(ctx, x_seq, v, v_threshold, v_reset, alpha, detach_reset, grad_surrogate_function_index)

static backward(ctx, grad_spike_seq, grad_v_next)

class spikingjelly.cext.neuron.BaseNode(v_threshold=1.0, v_reset=0.0, surrogate_function='ATan', alpha=2.0, detach_reset=False)

基类：torch.nn.modules.module.Module

reset()

extra_repr()

training: bool

class spikingjelly.cext.neuron.LIFNode(tau=100.0, detach_input=False, v_threshold=1.0, v_reset=0.0, surrogate_function='ATan', alpha=2.0, detach_reset=False)

基类：spikingjelly.cext.neuron.BaseNode

forward(dv: torch.Tensor)

extra_repr()

training: bool

class spikingjelly.cext.neuron.MultiStepLIFNode(tau=100.0, detach_input=False, v_threshold=1.0, v_reset=0.0, surrogate_function='ATan', alpha=2.0, detach_reset=False)

基类：spikingjelly.cext.neuron.LIFNode

forward(dv_seq: torch.Tensor)

training: bool

class spikingjelly.cext.neuron.IFNode(v_threshold=1.0, v_reset=0.0, surrogate_function='ATan', alpha=2.0, detach_reset=False)

基类：spikingjelly.cext.neuron.BaseNode

forward(dv: torch.Tensor)

training: bool

class spikingjelly.cext.neuron.MultiStepIFNode(v_threshold=1.0, v_reset=0.0, surrogate_function='ATan', alpha=2.0, detach_reset=False)

基类：spikingjelly.cext.neuron.IFNode

forward(dv_seq: torch.Tensor)

training: bool