nir.ir.linear#
Module Contents#
Classes#
Affine transform that linearly maps and translates the input signal. |
|
Linear transform without bias: |
|
Scales a signal by some values. |
- class nir.ir.linear.Affine#
Bases:
nir.ir.node.NIRNodeAffine transform that linearly maps and translates the input signal.
This is equivalent to the Affine transformation
Assumes a one-dimensional input vector of shape (N,).
\[y(t) = W*x(t) + b\]- weight: numpy.ndarray#
- bias: numpy.ndarray#
- input_type: Optional[Dict[str, numpy.ndarray]]#
- output_type: Optional[Dict[str, numpy.ndarray]]#
- metadata: Dict[str, Any]#
- __post_init__()#
- class nir.ir.linear.Linear#
Bases:
nir.ir.node.NIRNodeLinear transform without bias:
\[y(t) = W*x(t)\]- weight: numpy.ndarray#
- __post_init__()#
- class nir.ir.linear.Scale#
Bases:
nir.ir.node.NIRNodeScales a signal by some values.
This node is equivalent to the Hadamard product.
\[y(t) = x(t) \odot s\]- scale: numpy.ndarray#
- __post_init__()#