gnes.encoder.numeric.pooling module

class gnes.encoder.numeric.pooling.PoolingEncoder(pooling_strategy='REDUCE_MEAN', backend='numpy', *args, **kwargs)

Bases: gnes.encoder.base.BaseNumericEncoder

encode(data, *args, **kwargs)

masked_reduce_max(x, m)

masked_reduce_mean(x, m, jitter=1e-10)

minus_mask(x, m, offset=1e+30)

mul_mask(x, m)

post_init()

Declare class attributes/members that can not be serialized in standard way

train(*args, **kwargs)

Train the model, need to be overrided