torchsig.transforms.dataset_transforms

DatasetTransforms on DatasetSignal objects.

Classes

AGC	Automatic Gain Control performing sample-by-sample AGC algorithm.
AWGN	Apply Additive White Gaussian Noise to DatasetSignal.
AddSlope	Add the slope of each sample with its preceeding sample to itself.
AdditiveNoiseDatasetTransform	Apply wideband additive noise with specified parameters to DatasetSignal.
BlockAGC	Implements a large instantaneous jump in receiver gain.
CarrierPhaseOffsetDatasetTransform	Apply randomized phase offset to signal I/Q data.
ChannelSwap	Swaps the I and Q channels of complex input data.
ComplexTo2D	Converts IQ data to two channels (real and imaginary parts).
CutOut	Applies the CutOut transform operation in the time domain.
DatasetTransform	Dataset Transform base class
IQImbalanceDatasetTransform	Applies a set of IQImbalance effects to a DatasetSignal: amplitude, phase, and DC offset.
LocalOscillatorFrequencyDriftDatasetTransform	Apply LO frequency drift to DatasetSignal.
LocalOscillatorPhaseNoiseDatasetTransform	Applies LO phase noise to DatasetSignal.
NonlinearAmplifierDatasetTransform	Applies a memoryless nonlinear amplifier model to DatasetSignal.
PassbandRippleDatasetTransform	Applies a model of wideband analog filter passband ripple for DatasetSignals.
PatchShuffle	Randomly shuffle multiple local regions of samples.
QuantizeDatasetTransform	Quantize signal I/Q samples into specified levels with a rounding method.
RandomDropSamples	Randomly drop IQ samples from the input data of specified durations and with specified fill techniques: * ffill (front fill): replace drop samples with the last previous value. * bfill (back fill): replace drop samples with the next value. * mean: replace drop samples with the mean value of the full data. * zero: replace drop samples with zeros.
RandomMagRescale	Randomly apply a magnitude rescaling, emulating a change in a receiver's gain control.
SpectralInversionDatasetTransform	Invert spectrum of a DatasetSignal.
Spectrogram	Computes the spectogram of IQ data.
SpectrogramDropSamples	Randomly drop samples from the input data of specified durations and with specified fill techniques: * ffill (front fill): replace drop samples with the last previous value * bfill (back fill): replace drop samples with the next value * mean: replace drop samples with the mean value of the full data * zero: replace drop samples with zeros * low: replace drop samples with low power samples * min: replace drop samples with the minimum of the absolute power * max: replace drop samples with the maximum of the absolute power * ones: replace drop samples with ones
TimeReversal	Applies a time reversal to the input.
TimeVaryingNoise	Add time-varying noise to DatasetSignal regions.