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

Function DeterministicDropout

lingvo/core/py_utils.py:3978–4021  ·  view source on GitHub ↗

Similar to `tf.nn.dropout()`, but fully deterministic. Args: x: A float Tensor on which to apply dropout. keep_prob: A scalar `Tensor` of keep probability. seeds: A Tensor of shape [2]. 2 seeds for deterministic random number generator. noise_shape: A 1-D `Tensor` of type `i

(x, keep_prob, seeds, noise_shape=None, name=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 2

use_tpuFunction · 0.85
GetShapeFunction · 0.85

Tested by

no test coverage detected

Used in the wild real call sites across dependent graphs

searching dependent graphs…