torchsig.transforms.transforms

Transforms on Signal objects.

Classes

AWGN	Apply Additive White Gaussian Noise to signal.
AddSlope	Add the slope of each sample with its preceding sample to itself.
AdditiveNoise	Adds noise with specified properties to signal.
AdjacentChannelInterference	Apply adjacent channel interference to signal.
CarrierFrequencyDrift	Apply carrier frequency drift to signal.
CarrierPhaseNoise	Apply Carrier phase noise to signal.
CarrierPhaseOffset	Apply a randomized carrier phase offset to signal.
ChannelSwap	Swaps the I and Q channels of complex input data.
ClockDrift	Simulates a clock drift effect, which applies a random error to the sampling rate.
ClockJitter	Simulates a clock jitter effect, which applies a random error to the sampling phase.
CoarseGainChange	Apply a randomized instantaneous jump in signal magnitude to model an abrupt receiver gain change.
CochannelInterference	Apply cochannel interference to signal.
ComplexTo2D	Converts IQ data to two channels (real and imaginary parts).
CutOut	Applies the CutOut transform operation in the time domain.
DigitalAGC	Automatic Gain Control performing sample-by-sample AGC algorithm.
Doppler	Apply a wideband Doppler effect to signal.
Fading	Apply a channel fading model to signal.
IQImbalance	Apply a set of I/Q imbalance effects to a signal: amplitude, phase, and DC offset.
InterleaveComplex	Transforms a complex-valued array into a real-valued array of interleaved IQ values.
IntermodulationProducts	Apply simulated basebanded intermodulation products to a signal.
NonlinearAmplifier	Apply a memoryless nonlinear amplifier model to a signal.
PassbandRipple	Models analog filter passband ripple response for a signal.
PatchShuffle	Randomly shuffle multiple local regions of samples.
Quantize	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. Transform is based off of the TSAug Dropout Transform.
Shadowing	Apply channel shadowing effect across entire signal.
SignalTransform	Base class for performing transforms on Signal objects.
SpectralInversion	Inverts spectrum of complex signal data.
Spectrogram	Computes the spectogram of I/Q data.
SpectrogramDropSamples	Randomly drop samples from the input data of specified durations and with specified fill techniques.
SpectrogramImage	Transforms signal to a spectrogram image.
Spurs	Simulates spurs by adding tones into the receive signal.
TimeReversal	Apply a time reversal to the input.
TimeVaryingNoise	Add time-varying noise to signal regions.