Initialization of the Base Trainable object. Any learning procedure that leverages DN3atasets should subclass this base class. By default uses the SGD with momentum optimization. Parameters ---------- cuda : bool, string, None If bool
(self, lr=0.001, metrics=None, evaluation_only_metrics=None, l2_weight_decay=0.01, cuda=None, **kwargs)
source not stored for this graph (policy: none)
nothing calls this directly
no test coverage detected