1 EvlBackbone

vin.backbone_evl.EvlBackbone(config)

Frozen EVL backbone wrapper that exposes neck features and voxel grid pose.

1.1 Methods

Name	Description
forward	Run EVL and return the feature volumes needed by VIN.

1.1.1 forward

vin.backbone_evl.EvlBackbone.forward(efm)

Run EVL and return the feature volumes needed by VIN.

1.1.1.1 Parameters

Name	Type	Description	Default
efm	Mapping[str, Any]	Raw EFM snippet dict (unbatched `T×...` or batched `B×T×...`).	required

1.1.1.2 Returns

Name	Type	Description
	EvlBackboneOutput	`EvlBackboneOutput` with neck features and voxel grid pose.

# EvlBackbone { #aria_nbv.vin.backbone_evl.EvlBackbone }

```python
vin.backbone_evl.EvlBackbone(config)
```

Frozen EVL backbone wrapper that exposes neck features and voxel grid pose.

## Methods

| Name | Description |
| --- | --- |
| [forward](#aria_nbv.vin.backbone_evl.EvlBackbone.forward) | Run EVL and return the feature volumes needed by VIN. |

### forward { #aria_nbv.vin.backbone_evl.EvlBackbone.forward }

```python
vin.backbone_evl.EvlBackbone.forward(efm)
```

Run EVL and return the feature volumes needed by VIN.

#### Parameters {.doc-section .doc-section-parameters}

| Name   | Type                | Description                                                        | Default    |
|--------|---------------------|--------------------------------------------------------------------|------------|
| efm    | Mapping\[str, Any\] | Raw EFM snippet dict (unbatched ``T×...`` or batched ``B×T×...``). | _required_ |

#### Returns {.doc-section .doc-section-returns}

| Name   | Type              | Description                                                 |
|--------|-------------------|-------------------------------------------------------------|
|        | EvlBackboneOutput | `EvlBackboneOutput` with neck features and voxel grid pose. |