MCPcopy Create free account
hub / github.com/tensorflow/lingvo / FProp

Method FProp

lingvo/core/base_model.py:570–602  ·  view source on GitHub ↗

Forward propagation. This default `FProp` implementation here supports batch splitting in synchronous and asynchronous training when sub-classes implement `FPropTower`. Args: theta: A `.NestedMap` object containing weights' values of this layer and its children layers

(self, theta, input_batch)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

FPropDefaultThetaMethod · 0.95

Calls 2

_FPropSplitInputBatchMethod · 0.95
_FPropResultMethod · 0.95

Tested by

no test coverage detected