Compose¶
- class torcheeg.transforms.Compose(transforms: List[Callable])[source][source]¶
Compose several transforms together. Consistent with
torchvision.transforms.Compose
’s behavior.from torcheeg import transforms t = transforms.Compose([ transforms.ToTensor(), transforms.Resize(size=(64, 64)), transforms.RandomNoise(p=0.1), transforms.RandomMask(p=0.1) ]) t(eeg=torch.randn(128, 9, 9))['eeg'].shape >>> (128, 64, 64)
Compose
supports transformers with different data dependencies. The above example combines multiple torch-based transformers, the following example shows a sequence of numpy-based transformer.from torcheeg import transforms t = transforms.Compose([ transforms.BandDifferentialEntropy(), transforms.MeanStdNormalize(), transforms.ToGrid(DEAP_CHANNEL_LOCATION_DICT) ]) t(eeg=np.random.randn(32, 128))['eeg'].shape >>> (128, 9, 9)
- Parameters:
transforms (list) – The list of transforms to compose.