> ## 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.

# E0202 — InputShapeMismatch (backend)

> The input tensor was prepared for a different model than the one being run.

<Warning>E0202: input shape mismatch</Warning>

## What happened

A hardware backend received an input tensor with `got` features per timestep, but the model's first layer expects `expected` features.

## Why

The input was encoded or resized for a different model. Each compiled artifact has a fixed input dimension (stored in the first layer's `in_features`). If the encoder was configured for a different model size, the input will not match.

## How to fix

1. Use `thrindex.encoders` with the correct `n_channels` matching the model's first layer.
2. Check the artifact's input dimension: `thrindex doctor --check model.thx` prints `Dense N → M` for the first layer; `N` is the required input feature count.
3. Confirm you are loading the correct artifact for your encoder configuration.

## Example

```
E0202: input shape mismatch — expected 700 features, got 784
Why: the input tensor was prepared for a different model
Fix: re-encode inputs using `thrindex.encoders` with the model's declared input size
Docs: https://docs.thrindex.com/errors/E0202
```