MCPcopy Create free account
hub / github.com/alibaba/nann / dense

Function dense

tensorflow/tensorflow/python/layers/core.py:116–187  ·  view source on GitHub ↗

Functional interface for the densely-connected layer. This layer implements the operation: `outputs = activation(inputs * kernel + bias)` where `activation` is the activation function passed as the `activation` argument (if not `None`), `kernel` is a weights matrix created by the layer, a

(
    inputs, units,
    activation=None,
    use_bias=True,
    kernel_initializer=None,
    bias_initializer=init_ops.zeros_initializer(),
    kernel_regularizer=None,
    bias_regularizer=None,
    activity_regularizer=None,
    kernel_constraint=None,
    bias_constraint=None,
    trainable=True,
    name=None,
    reuse=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 15

bodyMethod · 0.85
testCallMethod · 0.85
testCallTensorDotMethod · 0.85
testNoBiasMethod · 0.85
testNonTrainableMethod · 0.85
testOutputShapeMethod · 0.85
testCallOnPlaceHolderMethod · 0.85
testActivationMethod · 0.85
testKernelRegularizerMethod · 0.85
testBiasRegularizerMethod · 0.85

Calls 2

DenseClass · 0.70
applyMethod · 0.45

Tested by 15

bodyMethod · 0.68
testCallMethod · 0.68
testCallTensorDotMethod · 0.68
testNoBiasMethod · 0.68
testNonTrainableMethod · 0.68
testOutputShapeMethod · 0.68
testCallOnPlaceHolderMethod · 0.68
testActivationMethod · 0.68
testKernelRegularizerMethod · 0.68
testBiasRegularizerMethod · 0.68