v0.7.2

What's Changed

• Add lowpass option for SNR calculation by @wbenoit26 in #202

Full Changelog: v0.7.1...v0.7.2

v0.7.1

What's Changed

• Fixes issue where tensors in waveform generator not getting built on correct device by @EthanMarx in #199

Full Changelog: v0.7.0...v0.7.1

v0.7.0

What's Changed

Features

• Add lowpass option to whitening by @wbenoit26 in #185
• Use relative imports by @ravioli1369 in #190
• Add fnames_per_batch argument to HDF5Dataset by @EthanMarx in #191
• SciPy filters by @ravioli1369 in #189
• Adds TimeDomainCBCWaveformGenerator by @EthanMarx in #188

Infrastructure Changes

• Add demo notebook by @wbenoit26 in #180
• Update readme and add license and citation by @wbenoit26 in #186
• Increased waveform tolerance by @wbenoit26 in #192
• Set random seed for unit tests by @wbenoit26 in #196
• Fix flaky tests by @EthanMarx in #197

Full Changelog: v0.6.3...v0.7.0

v0.6.3

What's Changed

• Create tensor on proper device in IMRPhenomPv2 by @EthanMarx in #183
• Set upper bound of "close" distance tests to 400 @EthanMarx in #184

Full Changelog: v0.6.2...v0.6.3

v0.6.2

What's Changed

• Directly restrict scipy in tox when running unit tests due to deprecation

Bug fixes

• Fixed discrepancy between torch and LAL IMRPhenomPv2 implementations #176
• Fixed bug when using batched inputs to IMRPhenomPV2 #181

v0.6.1

What's Changed

• Fix bug in fmaxCalc of PhenomD which was causing nans #172
• Add more robust waveform tests #172
• Adds conversion function for chirp mass and mass ratio to component masses #173

Full Changelog: v0.6.0...v0.6.1

v0.6.0

What's Changed

• Adds spline interpolation transform #157
• Standardizes IMRPhenomP and PhenomD API #167
• Adds option to regularize standard scaler #166
• Adds function for converting from bilby to lalsimulation spin parameters #168
• Refactors waveforms module, adding cbc and adhoc submodules #168

Bug Fixes

• Fixes bug when performing spectral density estimation with odd outputs #165

v0.5.1

What's Changed

• Constrained scipy to >=1.9 to avoid bug in median calculation in #154
• Switch type-checking library from torchtyping to jaxtyping in #153
• Add support for Python 3.12 in #156

Full Changelog: v0.5.0...v0.5.1

v0.5.0

What's Changed

• Added KAGRA as detector #132
• Added IMRPhenomP implementation #138
• SineGaussian returns polarizations in dtype of passed parameters #139
• Refactored TaylorF2 and IMRPhenomD into torch.nn.Modules #137
• Added dimensionality check to GroupNorm1D #134

Bug Fixes

• Fixed typehints in ml4gw.distributions module #129
• numpy version restricted to <2.0.0 #145

Full Changelog: v0.4.2...v0.5.0

v0.4.2

• InMemoryDataset now inherits from torch.utils.data.IterableDataset for compatibility with torch.utils.data.Dataloader #119
• ml4gw.distributions now inherit from torch.distributions module

Bug Fixes

• Fixed deprecation warning for use of torch.Tensor.T in ml4gw.waveforms.IMRPhenomD #114