MCPcopy Create free account
hub / github.com/SPOClab-ca/dn3 / __init__

Method __init__

dn3/trainable/processes.py:33–98  ·  view source on GitHub ↗

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 from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 4

add_metricsMethod · 0.95
build_networkMethod · 0.95
parametersMethod · 0.95
keysMethod · 0.80

Tested by

no test coverage detected