Expand description
The neural network module.
Functions§
- adaptive_
avg_ pool1d - Applies a 1D adaptive avg pooling.
- adaptive_
avg_ pool2d - Applies a 2D adaptive avg pooling.
- attention
- Computes scaled dot-product attention: softmax(QKᵗ * scale) · V,
where scale defaults to 1/sqrt(head_dim) (configurable via
options.scale). Optionally applies masking, additive bias, causal masking, and softcap. - attention_
fallback - Exports attention fallback to test backend’s attention against.
- avg_
pool1d - Applies a 1D avg pooling.
- avg_
pool2d - Applies a 2D avg pooling.
- conv1d
- Applies a 1D convolution.
- conv2d
- Applies a 2D convolution.
- conv3d
- Applies a 3D convolution.
- conv_
transpose1d - Applies a 1D transposed convolution.
- conv_
transpose2d - Applies a 2D transposed convolution.
- conv_
transpose3d - Applies a 3D transposed convolution](crate::ops::ModuleOps::conv_transpose3d).
- ctc_
loss - Computes the CTC loss.
- deform_
conv2d - Applies a Deformable 2D convolution.
- embedding
- Applies the embedding module.
- interpolate
- Applies a 2D interpolation.
- linear
- Applies a linear transformation to the input tensor using the given weight and bias.
- max_
pool1d - Applies a 1D max pooling.
- max_
pool1d_ with_ indices - Applies a 1D max pooling.
- max_
pool2d - Applies a 2D max pooling.
- max_
pool2d_ with_ indices - Applies a 2D max pooling with indices.
- unfold4d
- Applies a 4D to 3D unfold.