torchsig.transforms.functional

Functional transforms for reuse and custom fine-grained control

Functions

add_slope	Add slope between each sample and its preceding sample is added to every sample.
additive_noise	Additive complex noise with specified parameters.
adjacent_channel_interference	Adds adjacent channel interference to the baseband data at a specified center frequency and power level.
agc	Automatic Gain Control algorithm (deterministic).
awgn	Adds zero-mean complex additive white Gaussian noise with power of noise_power_db.
block_agc	Implements a large instantaneous jump in receiver gain.
channel_swap	Swap I and Q channels of IQ data.
cochannel_interference	Applies uncorrelated co-channel interference to the baseband data, modeled as shaped noise with specified parameters.
complex_to_2d	Converts IQ data to two channels (real and imaginary parts).
cut_out	Performs CutOut: replacing values with fill.
doppler	Applies wideband Doppler effect through time scaling.
drop_samples	Drop samples at given locations/durations with fill technique.
fading	Apply fading channel to signal.
intermodulation_products	Pass IQ data through an optimized memoryless nonlinear response model that creates local intermodulation distortion (IMD) products.
iq_imbalance	Applies IQ imbalance to IQ data.
local_oscillator_frequency_drift	Mixes data with a frequency drifting Local Oscillator (LO), with drift modeled as a random walk.
mag_rescale	Apply rescaling of input rescale starting at time start.
nonlinear_amplifier	A memoryless AM/AM, AM/PM nonlinear amplifier function-based model using a hyperbolic tangent output power response defined by gain and saturation power.
nonlinear_amplifier_table	A nonlinear amplifier (AM/AM, AM/PM) memoryless model that distorts an input complex signal to simulate an amplifier response, based on interpolating a table of provided power input, power output, and phase change data points.
normalize	Scale data so that a specfied norm computes to 1. For detailed information, see numpy.linalg.norm.()
passband_ripple	Functional for passband ripple transforms.
patch_shuffle	Apply shuffling of patches specified by num_patches.
phase_noise	Mixes data with a Local Oscillator (LO) with phase noise modeled as a Gaussian RV.
phase_offset	Applies a phase rotation to data.
quantize	Quantize input to number of levels specified.
shadowing	Applies RF shadowing to the data, assuming the channel obstructions' loss are lognormal.
spectral_inversion	Applies a spectral inversion to input data.
spectrogram	Computes spectrogram from IQ data.
spectrogram_drop_samples	Drop samples at given locations/durations with fill technique.
time_reversal	Applies time reversal to data (flips horizontally).
time_varying_noise	Adds time-varying complex additive white Gaussian noise with power levels in range (noise_power_low, noise_power_high) dB and with inflections number of inflection points spread over the input iq data randomly if random_regions is True or evenly spread if False.