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

Function fully_connected

tf_util.py:327–363  ·  view source on GitHub ↗

Fully connected layer with non-linear operation. Args: inputs: 2-D tensor BxN num_outputs: int Returns: Variable tensor of size B x num_outputs.

(inputs,
                    num_outputs,
                    scope,
                    use_xavier=True,
                    stddev=1e-3,
                    weight_decay=None,
                    activation_fn=tf.nn.relu,
                    bn=False,
                    bn_decay=None,
                    is_training=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 3

_variable_on_cpuFunction · 0.85
batch_norm_for_fcFunction · 0.85

Tested by

no test coverage detected