1 vin.encoders.fixed_fourier
vin.encoders.fixed_fourier
Fixed or directly learnable Fourier features for scalar VIN descriptors.
This module provides FourierFeatures, a small torch.nn.Module used by aria_nbv.vin.encoders.spherical.ShellShPoseEncoder to encode a one-dimensional candidate radius before projection. For the trainable MLP-based positional encoder used by VIN-Core, prefer aria_nbv.vin.encoders.fourier.LearnableFourierFeatures.
1.1 Classes
| Name | Description |
|---|---|
| FourierFeatures | Sin/cos Fourier features with optional learnable frequencies. |
| FourierFeaturesConfig | Config-as-factory wrapper for FourierFeatures. |
1.1.1 FourierFeatures
vin.encoders.fixed_fourier.FourierFeatures(config)Sin/cos Fourier features with optional learnable frequencies.
1.1.1.1 Parameters
| Name | Type | Description | Default |
|---|---|---|---|
| config | 'FourierFeaturesConfig' | Config-as-factory object defining input dimension, number of frequencies, raw-input concatenation, and frequency initialization. | required |
1.1.1.2 Attributes
| Name | Description |
|---|---|
| output_dim | Return the raw-input plus sine/cosine output width. |
1.1.1.3 Methods
| Name | Description |
|---|---|
| forward | Apply Fourier feature mapping to inputs. |
1.1.1.3.1 forward
vin.encoders.fixed_fourier.FourierFeatures.forward(x)Apply Fourier feature mapping to inputs.
1.1.1.3.1.1 Parameters
| Name | Type | Description | Default |
|---|---|---|---|
| x | Tensor | Tensor["... D", float32] input vectors. |
required |
1.1.1.3.1.2 Returns
| Name | Type | Description |
|---|---|---|
| Tensor | Tensor["... output_dim", float32] Fourier-encoded features. |
1.1.2 FourierFeaturesConfig
vin.encoders.fixed_fourier.FourierFeaturesConfig()Config-as-factory wrapper for FourierFeatures.
The emitted module has no hidden MLP; it only returns raw inputs and normalized sin/cos features. Use aria_nbv.vin.encoders.fourier.LearnableFourierFeaturesConfig when the projection should be followed by a trainable MLP.
1.1.2.1 Attributes
| Name | Description |
|---|---|
| target_type | Return the runtime module type constructed by this config. |
| input_dim | Input dimensionality. |
| num_frequencies | Number of Fourier frequencies. |
| include_input | Concatenate raw inputs to the Fourier features when True. |
| learnable | Whether the frequency matrix is learnable. |
| init_scale | Stddev used to initialize the frequency matrix. |