braindecode 1.8.1.dev172377786__tar.gz → 1.8.1.dev172419947__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {braindecode-1.8.1.dev172377786/braindecode.egg-info → braindecode-1.8.1.dev172419947}/PKG-INFO +1 -1
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/functional/_real_dft.py +55 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/functional/functions.py +13 -5
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/barista.py +2 -2
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eeginception_mi.py +7 -3
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegnex.py +1 -1
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegpt.py +3 -1
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/labram.py +19 -9
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/luna.py +3 -1
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/patchedtransformer.py +3 -7
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/reve.py +15 -4
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/attention.py +2 -2
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/dance_modules.py +16 -3
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/layers.py +41 -2
- braindecode-1.8.1.dev172419947/braindecode/version.py +1 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947/braindecode.egg-info}/PKG-INFO +1 -1
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/whats_new.rst +12 -0
- braindecode-1.8.1.dev172377786/braindecode/version.py +0 -1
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/LICENSE.txt +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/MANIFEST.in +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/NOTICE.txt +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/README.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/augmentation/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/augmentation/base.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/augmentation/functional.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/augmentation/transforms.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/classifier.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/_notebook_viewer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/base.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bbci.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bcicomp.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/datasets.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/format.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/hub.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/hub_format.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/hub_io.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/hub_validation.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/iterable.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/chb_mit.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/collate.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/mne.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/moabb.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/nmt.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/registry.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/siena.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/sleep_physio_challe_18.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/sleep_physionet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/tuh.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/utils.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/xy.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datautil/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datautil/channel_utils.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datautil/hub_formats.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datautil/serialization.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datautil/util.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/eegneuralnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/functional/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/functional/initialization.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/atcnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/attentionbasenet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/attn_sleep.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/axon.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/base.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/bendr.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/biot.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/brainbert.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/brainmodule.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/brainomni.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/brant.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/cbramod.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/codebrain.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/config.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/contrawr.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/csbrain.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/ctnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/dance.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/deep4.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/deepsleepnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/dgcnn.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/diver1.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eeg_clip.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegconformer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegdino.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eeginception_erp.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegitnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegminer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegsimpleconv.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegsym.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegtcnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/emg2qwerty.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/fbcnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/fblightconvnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/fbmsnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/guetschel2026.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/hybrid.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/ifnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/mapa.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/medformer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/meta_neuromotor.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/mirepnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/mscformer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/msvtnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/mvpformer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/neuropose.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/neurorvq.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/neurorvq_tokenizer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/popt.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/sccnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/seizure_transformer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/sensingdynamics.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/shallow_fbcsp.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/signal_jepa.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/sinc_shallow.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/sleep_stager_blanco_2020.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/sleep_stager_chambon_2018.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/sleepfm.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/sparcnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/sstdpn.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/steegformer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/summary.csv +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/syncnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/tcformer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/tcn.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/tfm_tokenizer.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/tidnet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/tmsanet.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/tsinception.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/usleep.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/util.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/vemg2pose.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/zuna.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/activation.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/blocks.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/channels.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/convolution.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/filter.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/linear.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/linear_attention.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/parametrization.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/popt_modules.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/quantization.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/stats.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/util.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/wrapper.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/preprocessing/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/preprocessing/eegprep_preprocess.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/preprocessing/mne_preprocess.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/preprocessing/preprocess.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/preprocessing/util.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/preprocessing/windowers.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/regressor.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/samplers/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/samplers/base.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/samplers/ssl.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/training/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/training/callbacks.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/training/losses.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/training/scoring.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/util.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/visualization/__init__.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/visualization/activations.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/visualization/attribution.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/visualization/confusion_matrices.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/visualization/frequency.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/visualization/metrics.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/visualization/sanity.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/visualization/topology.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode.egg-info/SOURCES.txt +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode.egg-info/dependency_links.txt +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode.egg-info/requires.txt +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode.egg-info/top_level.txt +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/Makefile +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/_templates/autosummary/class.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/_templates/autosummary/class_in_subdir.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/_templates/autosummary/function.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/_templates/autosummary/function_in_subdir.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/agent_docs.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/api.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/cite.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/conf.py +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/help.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/index.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/install/install.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/install/install_pip.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/install/install_source.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/attention.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/channel.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/convolution.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/filterbank.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/gnn.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/interpretable.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/lbm.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/recurrent.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/categorization/spd.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/models.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/models_categorization.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/models_table.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/models/models_visualization.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/sg_execution_times.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/docs/user_guide/channel_strategies.rst +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/pyproject.toml +0 -0
- {braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/setup.cfg +0 -0
{braindecode-1.8.1.dev172377786/braindecode.egg-info → braindecode-1.8.1.dev172419947}/PKG-INFO
RENAMED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: braindecode
|
|
3
|
-
Version: 1.8.1.
|
|
3
|
+
Version: 1.8.1.dev172419947
|
|
4
4
|
Summary: Deep learning software to decode EEG, ECG or MEG signals
|
|
5
5
|
Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Alexandre Gramfort <agramfort@meta.com>
|
|
6
6
|
Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>
|
|
@@ -12,8 +12,10 @@ never downcast, so callers wrap the numerically sensitive parts with
|
|
|
12
12
|
#
|
|
13
13
|
# License: BSD (3-clause)
|
|
14
14
|
import functools
|
|
15
|
+
from typing import Optional
|
|
15
16
|
|
|
16
17
|
import torch
|
|
18
|
+
from torch import nn
|
|
17
19
|
|
|
18
20
|
|
|
19
21
|
def needs_real_dft(x: torch.Tensor) -> bool:
|
|
@@ -136,3 +138,56 @@ def hilbert_freq_real(x: torch.Tensor, forward_fourier: bool) -> torch.Tensor:
|
|
|
136
138
|
return torch.stack((out_real, out_imag), dim=-1)
|
|
137
139
|
|
|
138
140
|
return compute(x)
|
|
141
|
+
|
|
142
|
+
|
|
143
|
+
@torch.jit.unused
|
|
144
|
+
def fft_conv1d_real(
|
|
145
|
+
x: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor]
|
|
146
|
+
) -> torch.Tensor:
|
|
147
|
+
"""Real-valued equivalent of :func:`braindecode.functional.fft_conv1d`.
|
|
148
|
+
|
|
149
|
+
Overlap-save: the input is cut into blocks of ``n`` samples (the power of
|
|
150
|
+
two ``>= 2 * kernel_size``) that advance by ``n - kernel_size + 1`` outputs,
|
|
151
|
+
each block's DFT is a matmul against the cosine/sine basis, and per
|
|
152
|
+
frequency the complex product with the kernels, summed over the input
|
|
153
|
+
channels, is one real matmul.
|
|
154
|
+
"""
|
|
155
|
+
|
|
156
|
+
@fp32_island
|
|
157
|
+
def compute(x, weight):
|
|
158
|
+
n_times, kernel_size = x.shape[-1], weight.shape[-1]
|
|
159
|
+
n = 1 << (2 * kernel_size - 1).bit_length()
|
|
160
|
+
hop = n - kernel_size + 1
|
|
161
|
+
n_blocks = -(-n_times // hop)
|
|
162
|
+
n_freqs = n // 2 + 1
|
|
163
|
+
# "same" alignment: torch pads the extra zero of an even kernel on the right
|
|
164
|
+
left = (kernel_size - 1) // 2
|
|
165
|
+
x = nn.functional.pad(x, (left, (n_blocks + 1) * hop - n_times - left))
|
|
166
|
+
hops = x.unflatten(-1, (n_blocks + 1, hop))
|
|
167
|
+
# block i = hop i + the first kernel_size - 1 samples of hop i + 1
|
|
168
|
+
blocks = torch.cat([hops[:, :, :-1], hops[:, :, 1:, : kernel_size - 1]], -1)
|
|
169
|
+
cosine, sine = real_dft_basis(n, device=x.device, dtype=x.dtype)
|
|
170
|
+
basis = torch.cat([cosine, -sine]).transpose(0, 1) # -> [Re | Im] of rfft
|
|
171
|
+
x_f = blocks @ basis # (batch, in, blocks, 2 * n_freqs)
|
|
172
|
+
w_f = nn.functional.pad(weight.to(x), (0, n - kernel_size)) @ basis
|
|
173
|
+
w_re, w_im = w_f[..., :n_freqs], w_f[..., n_freqs:]
|
|
174
|
+
# conv1d is a cross-correlation: x_f * conj(w_f), summed over the input
|
|
175
|
+
# channels. Per frequency [Re x, Im x] @ [[Re w, -Im w], [Im w, Re w]].
|
|
176
|
+
w_f = torch.cat([torch.cat([w_re, -w_im]), torch.cat([w_im, w_re])], 1)
|
|
177
|
+
x_f = x_f.unflatten(-1, (2, n_freqs)).permute(4, 0, 2, 3, 1).flatten(1, 2)
|
|
178
|
+
y_f = torch.bmm(x_f.flatten(2), w_f.permute(2, 1, 0)) # (freq, ., 2 * out)
|
|
179
|
+
y_f = y_f.unflatten(1, (x.shape[0], n_blocks)).unflatten(-1, (2, -1))
|
|
180
|
+
y_f = y_f.permute(1, 4, 2, 3, 0).flatten(
|
|
181
|
+
-2
|
|
182
|
+
) # (batch, out, blocks, 2 * n_freqs)
|
|
183
|
+
# inverse DFT of the first `hop` samples, the ones without wrap-around
|
|
184
|
+
scale = torch.full((n_freqs, 1), 2.0 / n, dtype=x.dtype, device=x.device)
|
|
185
|
+
scale[0] = 1.0 / n
|
|
186
|
+
scale[-1] = 1.0 / n # Nyquist (n is even)
|
|
187
|
+
inverse = torch.cat([scale * cosine[:, :hop], -scale * sine[:, :hop]])
|
|
188
|
+
return (y_f @ inverse).flatten(-2)[..., :n_times]
|
|
189
|
+
|
|
190
|
+
y = compute(x, weight)
|
|
191
|
+
if bias is not None:
|
|
192
|
+
y = y + bias.to(y).unsqueeze(-1)
|
|
193
|
+
return y.to(x)
|
|
@@ -62,9 +62,10 @@ def fft_conv1d(
|
|
|
62
62
|
|
|
63
63
|
Equal to the direct convolution up to float rounding: the FFT is long
|
|
64
64
|
enough for a linear (not circular) convolution. Its cost barely grows with
|
|
65
|
-
the kernel size, so it is faster than the direct one for long kernels
|
|
66
|
-
|
|
67
|
-
float32 (:func:`spectral_input`) and cast back.
|
|
65
|
+
the kernel size, so it is faster than the direct one for long kernels
|
|
66
|
+
(see :func:`prefer_fft_conv`). float16/bfloat16 inputs are computed in
|
|
67
|
+
float32 (:func:`spectral_input`) and cast back. On Intel Gaudi (HPU, no
|
|
68
|
+
complex dtype) the DFTs are real matmuls over overlapping blocks.
|
|
68
69
|
|
|
69
70
|
Parameters
|
|
70
71
|
----------
|
|
@@ -82,6 +83,8 @@ def fft_conv1d(
|
|
|
82
83
|
``x``. For an even ``kernel_size`` it is aligned like torch's
|
|
83
84
|
``padding="same"`` (the extra zero padded on the right).
|
|
84
85
|
"""
|
|
86
|
+
if _real_dft.needs_real_dft(x):
|
|
87
|
+
return _real_dft.fft_conv1d_real(x, weight, bias)
|
|
85
88
|
n_times, kernel_size = x.shape[-1], weight.shape[-1]
|
|
86
89
|
# >= n_times + kernel_size - 1 (no circular wrap-around), even and
|
|
87
90
|
# 5-smooth: the fast cases of a real FFT
|
|
@@ -115,8 +118,11 @@ def prefer_fft_conv(x: torch.Tensor, kernel_size: int) -> bool:
|
|
|
115
118
|
and from ``batch_size * kernel_size >= 600`` if also
|
|
116
119
|
``in_channels * kernel_size >= 120``: with one or two input channels a
|
|
117
120
|
float32 direct convolution stays cheaper up to k = 85 / 31 (13 long
|
|
118
|
-
temporal convolutions of the model zoo, 22 channels x batch 32).
|
|
119
|
-
|
|
121
|
+
temporal convolutions of the model zoo, 22 channels x batch 32). On Intel
|
|
122
|
+
Gaudi (HPU) a direct convolution costs about ``batch_size * n_times *
|
|
123
|
+
kernel_size`` and the FFT about a fixed few milliseconds in eager mode: the
|
|
124
|
+
FFT wins from 8 input channels and ``batch_size * n_times * kernel_size >=
|
|
125
|
+
8e6``. GPUs keep the direct convolution.
|
|
120
126
|
|
|
121
127
|
Parameters
|
|
122
128
|
----------
|
|
@@ -125,6 +131,8 @@ def prefer_fft_conv(x: torch.Tensor, kernel_size: int) -> bool:
|
|
|
125
131
|
kernel_size : int
|
|
126
132
|
Kernel length in samples.
|
|
127
133
|
"""
|
|
134
|
+
if x.device.type == "hpu":
|
|
135
|
+
return x.shape[1] >= 8 and x.shape[0] * x.shape[-1] * kernel_size >= 8e6
|
|
128
136
|
return x.device.type == "cpu" and (
|
|
129
137
|
x.element_size() == 2
|
|
130
138
|
or (x.shape[0] * kernel_size >= 600 and x.shape[1] * kernel_size >= 120)
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/barista.py
RENAMED
|
@@ -7,13 +7,13 @@ from __future__ import annotations
|
|
|
7
7
|
from typing import Optional
|
|
8
8
|
|
|
9
9
|
import torch
|
|
10
|
-
import torch.nn.functional as F
|
|
11
10
|
from einops.layers.torch import Rearrange
|
|
12
11
|
from torch import nn
|
|
13
12
|
|
|
14
13
|
from braindecode.models.base import EEGModuleMixin
|
|
15
14
|
from braindecode.models.util import extract_channel_locations_from_chs_info
|
|
16
15
|
from braindecode.modules import GatedLinearUnit, PatchTokenizer
|
|
16
|
+
from braindecode.modules.attention import _scaled_dot_product_attention
|
|
17
17
|
|
|
18
18
|
|
|
19
19
|
class BaRISTA(EEGModuleMixin, nn.Module, license="other"):
|
|
@@ -689,7 +689,7 @@ class _RotarySelfAttention(nn.Module):
|
|
|
689
689
|
|
|
690
690
|
# Dropout falls on the attention output rather than on the weights,
|
|
691
691
|
# through dropout_p, because the reference disables the latter outright.
|
|
692
|
-
attention =
|
|
692
|
+
attention = _scaled_dot_product_attention(query, key, value)
|
|
693
693
|
attention = self.dropout(attention)
|
|
694
694
|
attention = self.merge_heads(attention)
|
|
695
695
|
return self.o_proj(attention)
|
|
@@ -60,7 +60,7 @@ class EEGInceptionMI(EEGModuleMixin, nn.Module):
|
|
|
60
60
|
(:func:`~braindecode.functional.fft_conv1d`: same parameters, equal up
|
|
61
61
|
to float rounding) instead of a direct convolution. ``None`` (default)
|
|
62
62
|
decides per input with :func:`~braindecode.functional.prefer_fft_conv`
|
|
63
|
-
(FFT on CPU where it was faster in benchmarks, direct on GPU
|
|
63
|
+
(FFT on CPU and HPU where it was faster in benchmarks, direct on GPU).
|
|
64
64
|
|
|
65
65
|
References
|
|
66
66
|
----------
|
|
@@ -340,8 +340,12 @@ class _InceptionModuleMI(nn.Module):
|
|
|
340
340
|
X1 = torch.cat([conv(X1) for conv in self.conv_list], 1)
|
|
341
341
|
|
|
342
342
|
# channels_last: same values, but torch's CPU max pool then vectorises
|
|
343
|
-
# over channels instead of looping over them.
|
|
344
|
-
|
|
343
|
+
# over channels instead of looping over them. CPU only: on other
|
|
344
|
+
# devices the two layout copies cost more than they save.
|
|
345
|
+
X2 = X
|
|
346
|
+
if X.device.type == "cpu":
|
|
347
|
+
X2 = X.contiguous(memory_format=torch.channels_last)
|
|
348
|
+
X2 = self.pooling(X2)
|
|
345
349
|
# An even kernel_unit pools n_times + 1 samples: drop the last one.
|
|
346
350
|
X2 = self.pooling_conv(X2.contiguous())[..., : X.shape[-1]]
|
|
347
351
|
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegnex.py
RENAMED
|
@@ -356,7 +356,7 @@ class EEGNeX(EEGModuleMixin, nn.Module):
|
|
|
356
356
|
|
|
357
357
|
|
|
358
358
|
class _TemporalConv(nn.Conv2d):
|
|
359
|
-
"""``(1, k)`` Conv2d with "same" output length; on CPU, through
|
|
359
|
+
"""``(1, k)`` Conv2d with "same" output length; on CPU and HPU, through
|
|
360
360
|
:func:`~braindecode.functional.fft_conv1d` where
|
|
361
361
|
:func:`~braindecode.functional.prefer_fft_conv` expects it to be faster."""
|
|
362
362
|
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/eegpt.py
RENAMED
|
@@ -908,7 +908,9 @@ class _Attention(nn.Module):
|
|
|
908
908
|
# Reshape to (3, batch, num_heads, seq_len, head_dim)
|
|
909
909
|
qkv = qkv.reshape(qkv.shape[0], qkv.shape[1], 3, self.num_heads, -1)
|
|
910
910
|
qkv = qkv.permute(2, 0, 3, 1, 4)
|
|
911
|
-
|
|
911
|
+
# unbind, not qkv[0..2]: the backward of three selects writes three
|
|
912
|
+
# zero-filled copies of the whole qkv tensor and sums them.
|
|
913
|
+
q, k, v = qkv.unbind(0) # batch, num_heads, seq_len, head_dim
|
|
912
914
|
|
|
913
915
|
# 1. Rotary Positional Embeddings (RoPE)
|
|
914
916
|
# Unlike standard absolute positional encodings, RoPE rotates the
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/labram.py
RENAMED
|
@@ -19,6 +19,7 @@ from torch.nn.init import trunc_normal_
|
|
|
19
19
|
from braindecode.functional import rescale_parameter
|
|
20
20
|
from braindecode.models.base import EEGModuleMixin
|
|
21
21
|
from braindecode.modules import MLP, DropPath
|
|
22
|
+
from braindecode.modules.attention import _hpu_eager_fused_sdpa
|
|
22
23
|
from braindecode.modules.blocks import PatchTokenizer
|
|
23
24
|
|
|
24
25
|
# -----------------------------------------------------------------------------
|
|
@@ -1429,17 +1430,24 @@ class _Attention(nn.Module):
|
|
|
1429
1430
|
relative_position_bias.permute(2, 0, 1).contiguous().unsqueeze(0)
|
|
1430
1431
|
) # 1, nH, Wh*Ww, Wh*Ww
|
|
1431
1432
|
|
|
1432
|
-
# Fused kernel, same math. Not
|
|
1433
|
-
#
|
|
1434
|
-
|
|
1435
|
-
|
|
1436
|
-
|
|
1437
|
-
|
|
1438
|
-
|
|
1439
|
-
|
|
1433
|
+
# Fused kernel, same math. Not with attention dropout in training (it
|
|
1434
|
+
# would draw other masks). On Gaudi, torch's SDPA trains ~12 % slower
|
|
1435
|
+
# than the plain ops; the bridge's own fused kernel (eager mode, no
|
|
1436
|
+
# mask) is used instead.
|
|
1437
|
+
fused = not return_attention and (self.attn_drop.p == 0.0 or not self.training)
|
|
1438
|
+
out: Optional[torch.Tensor] = None
|
|
1439
|
+
if fused and q.device.type != "hpu":
|
|
1440
|
+
out = nn.functional.scaled_dot_product_attention(
|
|
1440
1441
|
q, k, v, attn_mask=attn_mask, scale=self.scale
|
|
1441
1442
|
)
|
|
1442
|
-
|
|
1443
|
+
elif (
|
|
1444
|
+
fused
|
|
1445
|
+
and attn_mask is None
|
|
1446
|
+
and not torch.jit.is_scripting()
|
|
1447
|
+
and (q.dtype == torch.float32 or q.dtype == torch.bfloat16)
|
|
1448
|
+
):
|
|
1449
|
+
out = _hpu_eager_fused_sdpa(q, k, v, self.scale)
|
|
1450
|
+
if out is None:
|
|
1443
1451
|
attn = (q * self.scale) @ k.transpose(-2, -1)
|
|
1444
1452
|
if attn_mask is not None:
|
|
1445
1453
|
attn = attn + attn_mask
|
|
@@ -1447,6 +1455,8 @@ class _Attention(nn.Module):
|
|
|
1447
1455
|
if return_attention:
|
|
1448
1456
|
return attn
|
|
1449
1457
|
x = attn @ v
|
|
1458
|
+
else:
|
|
1459
|
+
x = out
|
|
1450
1460
|
x = x.transpose(1, 2).reshape(B, N, -1)
|
|
1451
1461
|
|
|
1452
1462
|
x = self.proj(x)
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/luna.py
RENAMED
|
@@ -601,7 +601,9 @@ class _RotarySelfAttentionBlock(nn.Module):
|
|
|
601
601
|
.reshape(B, N, 3, self.num_heads, C // self.num_heads)
|
|
602
602
|
.permute(2, 0, 3, 1, 4)
|
|
603
603
|
) # (K, B, H, N, D)
|
|
604
|
-
|
|
604
|
+
# unbind, not qkv[0..2]: the backward of three selects writes three
|
|
605
|
+
# zero-filled copies of the whole qkv tensor and sums them.
|
|
606
|
+
q, k, v = qkv.unbind(0)
|
|
605
607
|
q = self._rotate_queries_or_keys(q)
|
|
606
608
|
k = self._rotate_queries_or_keys(k)
|
|
607
609
|
attn = F.scaled_dot_product_attention(
|
|
@@ -12,6 +12,7 @@ import torch.nn as nn
|
|
|
12
12
|
import torch.nn.functional as F
|
|
13
13
|
|
|
14
14
|
from braindecode.models.base import EEGModuleMixin
|
|
15
|
+
from braindecode.modules.attention import _scaled_dot_product_attention
|
|
15
16
|
|
|
16
17
|
|
|
17
18
|
class PBT(EEGModuleMixin, nn.Module):
|
|
@@ -411,13 +412,8 @@ class _MHSA(nn.Module):
|
|
|
411
412
|
k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
|
|
412
413
|
v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
|
|
413
414
|
|
|
414
|
-
y =
|
|
415
|
-
q,
|
|
416
|
-
k,
|
|
417
|
-
v,
|
|
418
|
-
attn_mask=None,
|
|
419
|
-
dropout_p=self.drop_prob if self.training else 0.0,
|
|
420
|
-
is_causal=False,
|
|
415
|
+
y = _scaled_dot_product_attention(
|
|
416
|
+
q, k, v, dropout_p=self.drop_prob if self.training else 0.0
|
|
421
417
|
)
|
|
422
418
|
|
|
423
419
|
# re-assemble heads -> (B, T, C)
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/models/reve.py
RENAMED
|
@@ -15,9 +15,10 @@ import torch
|
|
|
15
15
|
import torch.nn.functional as F
|
|
16
16
|
from mne.datasets.utils import _get_path
|
|
17
17
|
from torch import nn
|
|
18
|
-
from torch.nn import RMSNorm
|
|
19
18
|
|
|
20
19
|
from braindecode.models.base import EEGModuleMixin
|
|
20
|
+
from braindecode.modules.attention import _scaled_dot_product_attention
|
|
21
|
+
from braindecode.modules.layers import RMSNorm
|
|
21
22
|
|
|
22
23
|
logger = logging.getLogger(__name__)
|
|
23
24
|
|
|
@@ -439,7 +440,8 @@ class REVE(EEGModuleMixin, nn.Module):
|
|
|
439
440
|
raise ValueError(
|
|
440
441
|
"No positions provided and no default positions available. Please provide channel positions."
|
|
441
442
|
)
|
|
442
|
-
|
|
443
|
+
# One copy for the whole batch: the embedding below broadcasts.
|
|
444
|
+
pos = self.default_pos.unsqueeze(0).to(eeg.device)
|
|
443
445
|
|
|
444
446
|
pos = FourierEmb4D.add_time_patch(pos, n_patches)
|
|
445
447
|
# Positions stay in float32 for the Fourier features; the embedding
|
|
@@ -518,6 +520,7 @@ class GEGLU(nn.Module):
|
|
|
518
520
|
class FeedForward(nn.Module):
|
|
519
521
|
def __init__(self, dim: int, hidden_dim: int, geglu: bool):
|
|
520
522
|
super().__init__()
|
|
523
|
+
self.geglu = geglu
|
|
521
524
|
self.net = nn.Sequential(
|
|
522
525
|
RMSNorm(dim, eps=1e-6),
|
|
523
526
|
nn.Linear(dim, hidden_dim * 2 if geglu else hidden_dim, bias=False),
|
|
@@ -526,7 +529,15 @@ class FeedForward(nn.Module):
|
|
|
526
529
|
)
|
|
527
530
|
|
|
528
531
|
def forward(self, x: torch.Tensor) -> torch.Tensor:
|
|
529
|
-
|
|
532
|
+
if not self.geglu:
|
|
533
|
+
return self.net(x)
|
|
534
|
+
# GEGLU halves as two matmuls on the weight's row halves: contiguous
|
|
535
|
+
# outputs instead of strided views of one output (copied on HPU).
|
|
536
|
+
x = self.net[0](x)
|
|
537
|
+
weight = self.net[1].weight
|
|
538
|
+
half = weight.shape[0] // 2
|
|
539
|
+
x, gates = F.linear(x, weight[:half]), F.linear(x, weight[half:])
|
|
540
|
+
return self.net[3](F.gelu(gates) * x)
|
|
530
541
|
|
|
531
542
|
|
|
532
543
|
#################################################################################
|
|
@@ -554,7 +565,7 @@ class Attention(nn.Module):
|
|
|
554
565
|
q = q.unflatten(-1, (self.heads, -1)).transpose(1, 2)
|
|
555
566
|
k = k.unflatten(-1, (self.heads, -1)).transpose(1, 2)
|
|
556
567
|
v = v.unflatten(-1, (self.heads, -1)).transpose(1, 2)
|
|
557
|
-
out =
|
|
568
|
+
out = _scaled_dot_product_attention(q, k, v)
|
|
558
569
|
return self.to_out(out.transpose(1, 2).flatten(2))
|
|
559
570
|
|
|
560
571
|
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/attention.py
RENAMED
|
@@ -836,7 +836,7 @@ class CATLite(nn.Module):
|
|
|
836
836
|
|
|
837
837
|
@torch.jit.unused
|
|
838
838
|
def _hpu_eager_fused_sdpa(
|
|
839
|
-
query: Tensor, key: Tensor, value: Tensor
|
|
839
|
+
query: Tensor, key: Tensor, value: Tensor, scale: Optional[float] = None
|
|
840
840
|
) -> Optional[Tensor]:
|
|
841
841
|
# Lazy mode: None, the graph compiler already fuses torch's SDPA there.
|
|
842
842
|
from habana_frameworks.torch.utils.internal import is_lazy
|
|
@@ -845,7 +845,7 @@ def _hpu_eager_fused_sdpa(
|
|
|
845
845
|
return None
|
|
846
846
|
from habana_frameworks.torch.hpex.kernels import FusedSDPA
|
|
847
847
|
|
|
848
|
-
return FusedSDPA.apply(query, key, value, None, 0.0, False,
|
|
848
|
+
return FusedSDPA.apply(query, key, value, None, 0.0, False, scale, "None", False)
|
|
849
849
|
|
|
850
850
|
|
|
851
851
|
def _scaled_dot_product_attention(
|
|
@@ -10,11 +10,11 @@ import math
|
|
|
10
10
|
from typing import Dict, Optional
|
|
11
11
|
|
|
12
12
|
import torch
|
|
13
|
-
import torch.nn.functional as F
|
|
14
13
|
from torch import nn
|
|
15
14
|
|
|
16
15
|
from braindecode.functional import sinusoidal_positional_encoding
|
|
17
16
|
from braindecode.modules.activation import GatedLinearUnit
|
|
17
|
+
from braindecode.modules.attention import _scaled_dot_product_attention
|
|
18
18
|
from braindecode.modules.layers import ChannelMerger
|
|
19
19
|
|
|
20
20
|
|
|
@@ -28,7 +28,19 @@ class _ConvBlock(nn.Module):
|
|
|
28
28
|
self.act = None if last else activation()
|
|
29
29
|
|
|
30
30
|
def forward(self, x):
|
|
31
|
-
|
|
31
|
+
# Taps more than (T - 1) // dilation steps off-centre only ever read the
|
|
32
|
+
# zero padding: drop them (the same sum without its zero terms, fewer
|
|
33
|
+
# multiply-adds at long dilations).
|
|
34
|
+
d = self.conv.dilation[0]
|
|
35
|
+
half = self.conv.kernel_size[0] // 2
|
|
36
|
+
reach = (x.shape[-1] - 1) // d
|
|
37
|
+
if reach < half:
|
|
38
|
+
weight = self.conv.weight[:, :, half - reach : half + reach + 1]
|
|
39
|
+
x = nn.functional.conv1d(
|
|
40
|
+
x, weight, self.conv.bias, padding=reach * d, dilation=d
|
|
41
|
+
)
|
|
42
|
+
else:
|
|
43
|
+
x = self.conv(x)
|
|
32
44
|
if self.act is not None:
|
|
33
45
|
x = self.act(x)
|
|
34
46
|
return x
|
|
@@ -177,7 +189,8 @@ class _Attention(nn.Module):
|
|
|
177
189
|
q = q.unflatten(-1, (h, -1)).transpose(1, 2)
|
|
178
190
|
k = k.unflatten(-1, (h, -1)).transpose(1, 2)
|
|
179
191
|
v = v.unflatten(-1, (h, -1)).transpose(1, 2)
|
|
180
|
-
|
|
192
|
+
# scale = dim_head ** -0.5 = SDPA's default 1 / sqrt(q.shape[-1])
|
|
193
|
+
out = _scaled_dot_product_attention(q, k, v)
|
|
181
194
|
# (b, h, n, d) -> (b, n, h * d)
|
|
182
195
|
return self.to_out(out.transpose(1, 2).flatten(2))
|
|
183
196
|
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/modules/layers.py
RENAMED
|
@@ -9,10 +9,12 @@
|
|
|
9
9
|
from __future__ import annotations
|
|
10
10
|
|
|
11
11
|
import math
|
|
12
|
+
from typing import Optional
|
|
12
13
|
|
|
13
14
|
import torch
|
|
15
|
+
import torch.nn.functional as F
|
|
14
16
|
from einops.layers.torch import Rearrange
|
|
15
|
-
from torch import nn
|
|
17
|
+
from torch import Tensor, nn
|
|
16
18
|
|
|
17
19
|
from braindecode.functional import drop_path
|
|
18
20
|
|
|
@@ -331,5 +333,42 @@ class ChannelMerger(nn.Module):
|
|
|
331
333
|
scores = torch.einsum("bcd,bod->boc", [embedding, heads])
|
|
332
334
|
scores = scores + score_offset[:, None]
|
|
333
335
|
weights = torch.softmax(scores, dim=2).nan_to_num() # over n_chans
|
|
334
|
-
|
|
336
|
+
# (B, out, n_chans) @ (B, n_chans, T) -> (B, out, T). On HPU as
|
|
337
|
+
# (x^T @ weights^T)^T: Gaudi's lazy-mode graph compiler fails on
|
|
338
|
+
# ``weights @ x`` feeding a convolution's backward.
|
|
339
|
+
if x.device.type == "hpu":
|
|
340
|
+
out = (x.transpose(1, 2) @ weights.transpose(1, 2)).transpose(1, 2)
|
|
341
|
+
else:
|
|
342
|
+
out = weights @ x
|
|
335
343
|
return out # (B, out_channels, T)
|
|
344
|
+
|
|
345
|
+
|
|
346
|
+
@torch.jit.unused
|
|
347
|
+
def _hpu_fused_rms_norm(x: Tensor, weight: Tensor, eps: Optional[float]) -> Tensor:
|
|
348
|
+
from habana_frameworks.torch.hpex.normalization import FusedRMSNorm
|
|
349
|
+
|
|
350
|
+
return FusedRMSNorm.apply(
|
|
351
|
+
x, weight, torch.finfo(x.dtype).eps if eps is None else eps
|
|
352
|
+
)
|
|
353
|
+
|
|
354
|
+
|
|
355
|
+
class RMSNorm(nn.RMSNorm):
|
|
356
|
+
""":class:`torch.nn.RMSNorm`; Gaudi's fused kernel on HPU.
|
|
357
|
+
|
|
358
|
+
On HPU, torch's RMSNorm runs op by op (square, mean, rsqrt, two products,
|
|
359
|
+
and their backward ops). With a weight over the last dimension, in float32
|
|
360
|
+
or bfloat16, the bridge's fused kernel runs it instead. Same parameters and
|
|
361
|
+
state dict; other devices are unchanged.
|
|
362
|
+
"""
|
|
363
|
+
|
|
364
|
+
def forward(self, x: Tensor) -> Tensor:
|
|
365
|
+
if (
|
|
366
|
+
not torch.jit.is_scripting()
|
|
367
|
+
and x.device.type == "hpu"
|
|
368
|
+
and self.weight is not None
|
|
369
|
+
and len(self.normalized_shape) == 1
|
|
370
|
+
and x.dtype == self.weight.dtype
|
|
371
|
+
and (x.dtype == torch.float32 or x.dtype == torch.bfloat16)
|
|
372
|
+
):
|
|
373
|
+
return _hpu_fused_rms_norm(x, self.weight, self.eps)
|
|
374
|
+
return F.rms_norm(x, self.normalized_shape, self.weight, self.eps)
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
__version__ = "1.8.1.dev172419947"
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947/braindecode.egg-info}/PKG-INFO
RENAMED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: braindecode
|
|
3
|
-
Version: 1.8.1.
|
|
3
|
+
Version: 1.8.1.dev172419947
|
|
4
4
|
Summary: Deep learning software to decode EEG, ECG or MEG signals
|
|
5
5
|
Author-email: Robin Tibor Schirrmeister <robintibor@gmail.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Alexandre Gramfort <agramfort@meta.com>
|
|
6
6
|
Maintainer-email: Alexandre Gramfort <agramfort@meta.com>, Bruno Aristimunha Pinto <b.aristimunha@gmail.com>, Robin Tibor Schirrmeister <robintibor@gmail.com>
|
|
@@ -28,11 +28,15 @@ Current 1.8.1 (2026-08-31)
|
|
|
28
28
|
Enhancements
|
|
29
29
|
============
|
|
30
30
|
|
|
31
|
+
- :class:`braindecode.models.EEGInceptionMI` takes the channels-last copy for its max pooling only on CPU: on Intel Gaudi (HPU) the layout copies made the eager train step 2.6x slower than in 1.8.1 (now back to 1.8.1's time); CPU unchanged (:gh:`1344` by `Bruno Aristimunha`_).
|
|
32
|
+
- :func:`braindecode.functional.fft_conv1d` runs on Intel Gaudi (HPU) as overlap-save blocks with the DFT as real matmuls instead of a host FFT, and :func:`braindecode.functional.prefer_fft_conv` picks it there from 8 input channels and ``batch_size * n_times * kernel_size >= 8e6``: Gaudi eager train step of :class:`braindecode.models.EEGInceptionMI` 1.4-2.3x faster and :class:`braindecode.models.EEGNeX` 2.1x faster on 60-s windows at 100 Hz, batch 64; CPU unchanged; Gaudi outputs and gradients change by float rounding only (:gh:`1341` by `Bruno Aristimunha`_).
|
|
31
33
|
- :class:`braindecode.models.CSBrain` runs its region embedding and the region means of every encoder layer for all regions at once (a 0/1 neighbour-selection matmul and one batched matmul per kernel; one ``index_add_``) instead of one convolution and one mean per region: about half the operators per forward, CPU forward and train step 1.14-1.17x faster, Gaudi forward 1.30-1.45x and train step 1.36-1.56x faster; outputs change by float rounding only (:gh:`1335` by `Bruno Aristimunha`_).
|
|
32
34
|
- :class:`braindecode.models.DIVER1` computes the amplitude spectrum of its spectral embedding on the device on accelerators without complex tensors (Intel Gaudi / HPU) instead of a host FFT round trip: Gaudi forward 1.02-1.12x and train step 1.02-1.10x faster; CPU unchanged (:gh:`1334` by `Bruno Aristimunha`_).
|
|
33
35
|
- :class:`braindecode.models.DIVER1` builds and overlap-adds its STCPE sliding windows with one gather and one ``index_add`` instead of ``unfold``/``fold``: Gaudi forward 1.25-1.36x and train step 1.13-1.32x faster, CPU 0-1 % faster; outputs and released-checkpoint outputs unchanged, gradients change by float rounding only (:gh:`1333` by `Bruno Aristimunha`_).
|
|
36
|
+
- :class:`braindecode.models.REVE` computes the 4-D position embedding of its default channel positions once per forward and broadcasts it over the batch instead of computing it for one identical copy per example: 3 ms instead of 10-12 ms of each Gaudi train step (21 channels x 6000 samples, batch 64; step 1.01x); explicit ``pos`` inputs are unchanged (:gh:`1347` by `Bruno Aristimunha`_).
|
|
34
37
|
- :class:`braindecode.models.ContraWR` computes its STFT magnitude on the device on accelerators without complex tensors (Intel Gaudi / HPU) instead of a host STFT and a host-to-device copy of the spectrogram: Gaudi forward 4.2-7.1x and train step 2.4-5.2x faster; CPU unchanged (:gh:`1332` by `Bruno Aristimunha`_).
|
|
35
38
|
- :class:`braindecode.models.NeuroRVQTokenizer` sums the per-code counts and vectors of its EMA codebook update with ``index_add_`` instead of a dense one-hot matrix and GEMM: CPU train step 1.3x faster (22 channels, batch 32, 2 threads), Gaudi unchanged; outputs, gradients and token ids unchanged, the updated codebooks change by float rounding only (:gh:`1308` by `Bruno Aristimunha`_).
|
|
39
|
+
- :class:`braindecode.models.REVE` computes the two halves of its GEGLU feed-forward as two matrix products on the row halves of the same weight instead of slicing one product, so the activation reads contiguous tensors (HPU copied the strided halves in both passes). Same parameters and state dict; train step 1.11x faster on Gaudi eager and 1.06x on CPU (21 channels x 6000 samples, batch 64), float32 rounding differences only (:gh:`1346` by `Bruno Aristimunha`_).
|
|
36
40
|
- ``braindecode.modules.EMACodebook`` sums its training EMA statistics per code with ``index_add_`` instead of a dense one-hot matrix and GEMM: :class:`braindecode.models.TFMTokenizer` CPU train step 5 % faster and :class:`braindecode.models.BrainTokenizer` 1-3 % (22 channels, batch 32, 2 threads); outputs, gradients and token ids unchanged, the EMA buffers change by float rounding only (:gh:`1306` by `Bruno Aristimunha`_).
|
|
37
41
|
- The TUH datasets read the ``_date.txt`` file kept beside each EDF with :func:`json.load` instead of :func:`pandas.read_json`: 2.9 s -> 0.04 s for the 2993 TUAB date files; descriptions unchanged (:gh:`1300` by `Bruno Aristimunha`_).
|
|
38
42
|
- Add :class:`braindecode.models.Guetschel2026`, the encoder shared by the 58 MAE and JEPA
|
|
@@ -45,11 +49,19 @@ Enhancements
|
|
|
45
49
|
- :class:`braindecode.models.MetaNeuromotorHand` sums the cross-spectral bins of each frequency band with one einsum instead of a broadcast product and a sum: CPU forward and train step 3-7 % faster, Gaudi 2-10 % faster; outputs and gradients differ from before by more than float32 rounding (up to 1.6x master's own float32-vs-float64 difference, amplified by the eigendecomposition), argmax unchanged (:gh:`1330` by `Bruno Aristimunha`_).
|
|
46
50
|
- :class:`braindecode.models.MetaNeuromotorHand` rotates and half-vectorizes the MPF matrices with one precomputed ``index_select`` instead of three rolls, a stack and a permute copy: CPU train step about 2 % faster, Gaudi neutral; outputs, gradients and state dict unchanged bit for bit (:gh:`1292` by `Bruno Aristimunha`_).
|
|
47
51
|
- :class:`braindecode.models.MetaNeuromotorHand` solves the eigendecompositions of its matrix logarithm in chunks on all CPU threads instead of one matrix after another on one thread (torch's CPU ``eigh``): train step 2.5x faster at 24 threads (21 channels x 32,000 samples, batch 64), 11-15 % at 2 threads (batch 32), 1.5x on Gaudi (the featurizer runs on the host CPU); bit-identical outputs and gradients (:gh:`1336` by `Bruno Aristimunha`_).
|
|
52
|
+
- Add ``braindecode.modules.layers.RMSNorm``, a drop-in :class:`torch.nn.RMSNorm` (same parameters and state dict) that runs the Gaudi bridge's fused RMSNorm kernel on HPU instead of torch's op-by-op square, mean, rsqrt and products (float32 or bfloat16 input with a weight over the last dimension; other devices unchanged). :class:`braindecode.models.REVE` uses it: Gaudi train step 1.05x faster in eager mode and 1.03x in lazy mode (21 channels x 6000 samples, batch 64), differences within the Gaudi float32 error (:gh:`1348` by `Bruno Aristimunha`_).
|
|
48
53
|
- :class:`braindecode.models.CodeBrain` skips the attention scores in eval mode on CPU at the default ``swa_window_size=1``, where the window keeps only the diagonal and the attention reduces to its value projection: CPU eval forward 1.25x faster at 19 x 6000 (batch 32); training unchanged; outputs unchanged bit for bit (:gh:`1293` by `Bruno Aristimunha`_).
|
|
49
54
|
- :class:`braindecode.models.CodeBrain` takes the same one-wide-window shortcut in training on CPU: the attention weights are exactly one-hot, so the block multiplies the value projection by the diagonal of the dropout mask that :class:`torch.nn.MultiheadAttention` draws (same RNG stream) instead of computing all scores, their softmax, dropout and product: train step 1.2x faster at 21 x 6000 (batch 64, 24 threads) and 1.3x at 19 x 6000 (batch 32, 2 threads); outputs, gradients and dropout masks unchanged bit for bit (:gh:`1339` by `Bruno Aristimunha`_).
|
|
50
55
|
- :class:`braindecode.models.CodeBrain` computes its bidirectional long convolution as a linear convolution at a 5-smooth FFT length instead of a circular one of length 2 * seq_len: Gaudi forward 2.1x and train step 1.4x faster (19 channels x 6000 samples, batch 32), CPU forward 1-16 % faster, CPU train step unchanged to 6 % faster; outputs and gradients differ from before by more than float32 rounding (up to 1.9x master's own float32-vs-float64 difference on the released checkpoint's logits), argmax unchanged (:gh:`1329` by `Bruno Aristimunha`_).
|
|
51
56
|
- :class:`braindecode.models.MAPA` folds the (batch, array) axes before its within-array attention, so CPU attention runs as one fused 4-D :func:`torch.nn.functional.scaled_dot_product_attention` call instead of the 5-D math fallback: CPU forward 1.16x and train step 1.03x faster at 22 contacts (batch 32), 4.2 GB less peak memory in training; Gaudi unchanged; outputs and gradients change by float rounding only (relative differences below 1e-6) (:gh:`1294` by `Bruno Aristimunha`_).
|
|
52
57
|
- :class:`braindecode.modules.MultiHeadAttention` (EEGConformer, CTNet, MSCFormer, MIRepNet, STEEGFormer) and :class:`braindecode.models.ZUNA` run attention through the Gaudi bridge's fused SDPA kernel in HPU eager mode, where torch's SDPA runs op by op through the full score matrix (without a mask or dropout; lazy mode, CPU and other devices unchanged): Gaudi eager train step STEEGFormer 2.2x and ZUNA 1.7x faster (21 channels x 6000 samples), forward 1.2-2x for the other models; differences within the Gaudi float32 error (:gh:`1338` by `Bruno Aristimunha`_).
|
|
58
|
+
- :class:`braindecode.models.PBT` runs its attention through the shared SDPA helper of :class:`braindecode.modules.MultiHeadAttention`, so in HPU eager mode attention without dropout (eval mode, ``drop_prob=0``) uses the Gaudi bridge's fused SDPA kernel instead of the op-by-op path through the full score matrix: Gaudi eager forward 2.0x faster (21 channels x 6000 samples, batch 64); training with attention dropout, lazy mode, CPU and other devices unchanged (outputs, gradients and dropout draws identical); eval outputs within the Gaudi float32 error (:gh:`1350` by `Bruno Aristimunha`_).
|
|
59
|
+
- :class:`braindecode.models.DANCE` skips the taps of its dilated convolutions that only ever read the zero padding (kernel offset at or beyond the input length): CPU train step 0.92x and Gaudi eager 0.97x (21 channels x 6000 samples, batch 64); outputs change by float rounding only (:gh:`1343` by `Bruno Aristimunha`_).
|
|
60
|
+
- :class:`braindecode.modules.ChannelMerger` (DANCE, ``BrainModule(use_merger=True)``) computes its channel mix as ``(x^T @ weights^T)^T`` on HPU, where Gaudi's lazy-mode graph compiler failed on ``weights @ x`` feeding a convolution's backward: DANCE now trains in Gaudi lazy mode (train step 622 ms vs 844 ms in eager mode, 21 channels x 6000 samples, batch 64); other devices run the same code as before (:gh:`1351` by `Bruno Aristimunha`_).
|
|
61
|
+
- :class:`braindecode.models.Labram` and :class:`braindecode.models.BaRISTA` run attention through the Gaudi bridge's fused SDPA kernel in HPU eager mode (without a mask or attention dropout; lazy mode, CPU and other devices unchanged): Gaudi eager train step Labram 8 % and BaRISTA 5 % faster (21 channels x 6000 samples), differences within the Gaudi float32 error (:gh:`1342` by `Bruno Aristimunha`_).
|
|
62
|
+
- :class:`braindecode.models.DANCE` runs its Perceiver attention through the same Gaudi fused SDPA path in HPU eager mode (torch's SDPA there computes the full score matrix op by op, which made the DANCE Gaudi eager train step 8 % slower than in 1.8.1): Gaudi eager train step 848 -> 763 ms (21 channels x 6000 samples, batch 64); CPU and Gaudi lazy mode unchanged (:gh:`1340` by `Bruno Aristimunha`_).
|
|
63
|
+
- :class:`braindecode.models.REVE` runs its attention through the same helper, so HPU eager mode uses the Gaudi bridge's fused SDPA kernel instead of torch's op-by-op SDPA through the full score matrix (lazy mode, CPU and other devices unchanged): Gaudi eager train step 1.42x faster (21 channels x 6000 samples, batch 64); differences within the Gaudi float32 error (:gh:`1345` by `Bruno Aristimunha`_).
|
|
64
|
+
- :class:`braindecode.models.EEGPT` and :class:`braindecode.models.LUNA` split their fused query/key/value projection with ``unbind`` instead of three index selects, whose backward wrote a zero-filled copy of the whole projection gradient per select and summed them: EEGPT train step 1.09x faster on CPU and 1.02-1.03x on Gaudi (21 channels x 6000 samples, batch 64); outputs and gradients unchanged bit for bit (:gh:`1352` by `Bruno Aristimunha`_).
|
|
53
65
|
- :class:`braindecode.models.NeuroRVQ` and :class:`braindecode.models.NeuroRVQTokenizer` run their four temporal scales through the shared transformer blocks as one stacked batch on accelerators (CPU, and training with dropout, keep the per-scale loop): Gaudi train step 1.7-2.6x and forward 1.8-3.1x faster; CPU unchanged; outputs and token ids unchanged on CPU, within float rounding on Gaudi (:gh:`1312` by `Bruno Aristimunha`_).
|
|
54
66
|
- :class:`braindecode.datasets.TUH`, :class:`braindecode.datasets.TUHAbnormal` and :class:`braindecode.datasets.TUHEvents` build the standard_1005 montage once per process instead of twice per recording for ``rename_channels`` / ``set_montage``: 2993 TUAB recordings, ``rename_channels`` + ``set_montage`` 37.5 s -> 14.5 s (2.6x), 23 s less per ``TUHAbnormal`` indexing with ``n_jobs=1``; channel names, types, positions and descriptions unchanged (:gh:`1299` by `Bruno Aristimunha`_).
|
|
55
67
|
- The attention of :class:`braindecode.models.Labram` (shared by :class:`braindecode.models.NeuroRVQ` and :class:`braindecode.models.NeuroRVQTokenizer`) runs through :func:`torch.nn.functional.scaled_dot_product_attention` with the relative position bias as attn_mask off HPU (the manual path stays on HPU, with ``return_attention=True`` and with attention dropout in training): Labram CPU forward 1.2-1.3x and train step 1.06-1.14x faster, NeuroRVQ / NeuroRVQTokenizer CPU up to 6 % faster, Gaudi unchanged; outputs and gradients differ from before by more than float32 rounding (up to 2.5x master's own float32-vs-float64 difference on the released Labram checkpoint's gradients), token ids unchanged in single forward passes (:gh:`1328` by `Bruno Aristimunha`_).
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
__version__ = "1.8.1.dev172377786"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/augmentation/base.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/base.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bbci.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bcicomp.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/bids/hub.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/chb_mit.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/collate.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/mne.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/moabb.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/nmt.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/registry.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/siena.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/tuh.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/utils.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datasets/xy.py
RENAMED
|
File without changes
|
{braindecode-1.8.1.dev172377786 → braindecode-1.8.1.dev172419947}/braindecode/datautil/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|