MCPcopy Create free account
hub / github.com/XLechter/PCAN / _variable_with_weight_decay

Function _variable_with_weight_decay

tf_util.py:24–49  ·  view source on GitHub ↗

Helper to create an initialized Variable with weight decay. Note that the Variable is initialized with a truncated normal distribution. A weight decay is added only if one is specified. Args: name: name of the variable shape: list of ints stddev: standard deviation of a truncated

(name, shape, stddev, wd, use_xavier=True)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 5

conv1dFunction · 0.85
conv2dFunction · 0.85
conv2d_transposeFunction · 0.85
conv3dFunction · 0.85
fully_connectedFunction · 0.85

Calls 1

_variable_on_cpuFunction · 0.85

Tested by

no test coverage detected