torchsig.transforms.signal_transforms.SignalTransform¶
- class torchsig.transforms.signal_transforms.SignalTransform(measure=None, **kwargs)[source]¶
Bases:
TransformSignalTransform parent class.
Methods
Add parent Seedable object and set up RNGs accordingly
get_distributionGets second seed, usually used to seed both torch and numpy generators with slightly different seeds
Seed number generators with given seed.
Initialize torch and numpy number generators, and update its children.
Updates bookkeeping to transforms in Signal's SignalMetadata and checks signal valididty.
Update numpy and torch number generators with parent seed
- update(signal: Signal) None[source]¶
Updates bookkeeping to transforms in Signal’s SignalMetadata and checks signal valididty. Inherited classes should always call self.update() after performing transform operation (inside __call__).
- Parameters:
signal (Signal) – Transformed signal.
- __call__(signal: Signal) Signal[source]¶
Performs transforms.
- Parameters:
signal (Signal) – Signal to be transformed.
- Raises:
NotImplementedError – Inherited classes must override this method.
- Returns:
Transformed Signal.
- Return type:
- __init__(measure=None, **kwargs)¶
Transform initialization as Seedable.
- __repr__() str¶
Transform string representation. Should be able to recreate class from this string.
- Returns:
Transform representation.
- Return type: