tether.data package

Submodules

tether.data.encoding module

class tether.data.encoding.SpikingDatasetWrapper(dataset, encode_fn)[source]

Bases: Dataset

Wraps a standard dataset and applies an encoding function to the input.

tether.data.encoding.latency_encoding(x, n_steps, tau=1.0, threshold=0.01)[source]

Convert continuous values to spike trains using latency encoding. Higher values fire earlier.

Parameters:

  • x (torch.Tensor) – Input tensor.

  • n_steps (int) – Number of time steps.

  • tau (float) – Time constant.

  • threshold (float) – Threshold below which no spike is generated.

Returns:

Spike tensor with shape (n_steps, *x.shape).

Return type:

torch.Tensor

tether.data.encoding.rate_encoding(x, n_steps, gain=1.0)[source]

Convert continuous values to spike trains using rate encoding (Bernoulli).

Parameters:

  • x (torch.Tensor) – Input tensor with continuous values (usually in [0, 1]).

  • n_steps (int) – Number of time steps to simulate.

  • gain (float) – Scaling factor for firing probability.

Returns:

Spike tensor with shape (n_steps, *x.shape).

Return type:

torch.Tensor

Module contents

class tether.data.SpikingDatasetWrapper(dataset, encode_fn)[source]

Bases: Dataset

Wraps a standard dataset and applies an encoding function to the input.

tether.data.latency_encoding(x, n_steps, tau=1.0, threshold=0.01)[source]

Convert continuous values to spike trains using latency encoding. Higher values fire earlier.

Parameters:

  • x (torch.Tensor) – Input tensor.

  • n_steps (int) – Number of time steps.

  • tau (float) – Time constant.

  • threshold (float) – Threshold below which no spike is generated.

Returns:

Spike tensor with shape (n_steps, *x.shape).

Return type:

torch.Tensor

tether.data.rate_encoding(x, n_steps, gain=1.0)[source]

Convert continuous values to spike trains using rate encoding (Bernoulli).

Parameters:

  • x (torch.Tensor) – Input tensor with continuous values (usually in [0, 1]).

  • n_steps (int) – Number of time steps to simulate.

  • gain (float) – Scaling factor for firing probability.

Returns:

Spike tensor with shape (n_steps, *x.shape).

Return type:

torch.Tensor