MCPcopy Create free account
hub / github.com/YichenGong/Densely-Interactive-Inference-Network / normalize

Function normalize

python/models/attmix_CNN.py:1486–1513  ·  view source on GitHub ↗

Applies layer normalization. Args: inputs: A tensor with 2 or more dimensions, where the first dimension has `batch_size`. epsilon: A floating number. A very small number for preventing ZeroDivision Error. scope: Optional scope for `variable_scope`. reuse: Bo

(inputs, 
              epsilon = 1e-8,
              scope="ln",
              reuse=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 4

model_one_sideMethod · 0.85
self_attention_layerFunction · 0.85
dense_net_blockFunction · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected