Need some sort of top-level container for multiple datasets

SPOClab-ca / dn3

The fusion of MNE and PyTorch for accelerated deep-neural-network based BCI-systems and Neurophysiology signal analysis.

BSD 3-Clause "New" or "Revised" License

65 stars 19 forks source link

Need some sort of top-level container for multiple datasets #15

Closed kostasde closed 4 years ago

kostasde commented 4 years ago

The current dn3 philosophy is to provide convenience methods for each tier of data abstraction. Currently this is missing at the dataset level, and could be fixed with a basic object for now (extend experiment?) that can be leveraged in the future as this idea is explored.

kostasde commented 4 years ago

This ideally will have options that cover dataset oversampling/balancing