gnes.encoder.image.cvae module

class gnes.encoder.image.cvae.CVAEEncoder(model_dir, latent_dim=300, select_method='MEAN', l2_normalize=False, use_gpu=True, *args, **kwargs)[source]

Bases: gnes.encoder.base.BaseImageEncoder

batch_size = 64
encode(img, *args, **kwargs)[source]
Return type:ndarray
post_init()[source]

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

train(*args, **kwargs)

Train the model, need to be overrided