braindecode.augmentation.FrequencyShift¶
- class braindecode.augmentation.FrequencyShift(probability, sfreq, max_delta_freq=2, random_state=None)¶
Add a random shift in the frequency domain to all channels.
Note that here, the shift is the same for all channels of a single example.
- Parameters
- probabilityfloat
Float setting the probability of applying the operation.
- sfreqfloat
Sampling frequency of the signals to be transformed.
- max_delta_freqfloat | torch.Tensor, optional
Maximum shift in Hz that can be sampled (in absolute value). Defaults to 2 (shift sampled between -2 and 2 Hz).
- random_state: int | numpy.random.Generator, optional
Seed to be used to instantiate numpy random number generator instance. Defaults to None.
Methods
- get_params(*batch)¶
Return transform parameters.
- Parameters
- Xtensor.Tensor
The data.
- ytensor.Tensor
The labels.
- Returns
- paramsdict
Contains
- delta_freqfloat
The amplitude of the frequency shift (in Hz).
- sfreqfloat
Sampling frequency of the signals to be transformed.
- static operation(X, y, delta_freq, sfreq)¶
Adds a shift in the frequency domain to all channels.
Note that here, the shift is the same for all channels of a single example.
- Parameters
- Xtorch.Tensor
EEG input example or batch.
- ytorch.Tensor
EEG labels for the example or batch.
- delta_freqfloat
The amplitude of the frequency shift (in Hz).
- sfreqfloat
Sampling frequency of the signals to be transformed.
- Returns
- torch.Tensor
Transformed inputs.
- torch.Tensor
Transformed labels.
