gnes.encoder.numeric.vlad module¶

class gnes.encoder.numeric.vlad.VladEncoder(num_clusters, using_faiss_pred=False, *args, **kwargs)[source]¶

Bases: gnes.encoder.base.BaseNumericEncoder

batch_size = 2048¶

encode(vecs, *args, **kwargs)[source]¶

Return type:	`ndarray`

faiss_index()[source]¶

kmeans_pred(vecs)[source]¶

kmeans_train(vecs)[source]¶

train(vecs, *args, **kwargs)[source]¶: Train the model, need to be overrided