qbiocode.embeddings.compute_autoencoder module

Convolutional autoencoder embedding.

Importing this module maps torch – and so torch’s copy of libomp – into the process. On macOS that must not happen before xgboost’s copy is initialised or XGBoost model fitting segfaults; see qbiocode.utils._openmp for the full diagnosis. The preload below makes this module safe to import on its own, in any order, rather than relying on the caller having imported qbiocode first.

Summary

Classes:

ConvAutoencoder

Reference

class ConvAutoencoder

Bases: Module

forward(x)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.