> ## Documentation Index
> Fetch the complete documentation index at: https://docs.thrindex.com/llms.txt
> Use this file to discover all available pages before exploring further.

# E0407 — TemporalInputNotSupported

> run_batch received inputs with T > 1 timesteps. akida-akd1500 is a stateless single-frame backend that requires T = 1.

<Warning>E0407: akida-akd1500 requires T = 1 per sample</Warning>

## What happened

`run_batch` was called with inputs where at least one sample has more than one timestep (`T > 1`). The `akida-akd1500` backend requires exactly one timestep frame per sample.

## Why

AKD1500 processes **one spatial frame per `model.forward()` call**. It holds no temporal state between calls:

* There is no membrane potential that accumulates across timesteps.
* There is no recurrent architecture.
* There is no frame-to-frame buffering.

Iterating `T` frames independently through the same stateless model produces `T` independent feedforward responses. This is **not** equivalent to `T` timesteps of SNN temporal dynamics. A model whose behaviour depends on cross-timestep membrane accumulation will produce silently incorrect output rather than a recognisable error.

E0407 is raised explicitly to prevent that silent failure.

## How to fix

**Pass exactly one timestep frame per sample.** AKD1500 performs spatial inference; the timestep dimension must always be 1:

```python theme={null}
# Correct: [N_samples, T=1, features]
inputs = [[[0.5, 0.2, 0.8, ...]]]  # one sample, one frame

# Incorrect: [N_samples, T=10, features]
# inputs = [[[...], [...], ...]]  # 10 frames — will raise E0407
```

**For temporal SNN inference**, use the `sim` backend. The simulator implements full LIF temporal dynamics across any number of timesteps:

```python theme={null}
thx.compile(model, "model.thx", target="sim")
```

## Example

```
E0407: run_batch received inputs with T=10 timesteps per sample; akida-akd1500 requires T=1.
Observed: inputs shape [batch=4, T=10, features=700]; T > 1.
Why: AKD1500 processes one spatial frame per model.forward() call. It holds no temporal
     state between calls. Iterating T frames independently produces T independent feedforward
     responses — NOT equivalent to T timesteps of SNN temporal dynamics.
What to do: Pass exactly one timestep frame per sample: inputs shape [batch, 1, features].
            For temporal SNN inference, use the 'sim' backend.
Docs: https://docs.thrindex.com/errors/E0407
```