InputPorts
is an option to specify the number, names or shapes of input ports for some neural net layers.
Details
- InputPorts is typically used in layers that support an arbitrary number of input ports, such as ThreadingLayer, CatenateLayer, DotLayer and PlaceholderLayer.
- Typical settings for InputPorts include:
-
Automatic infer number of ports and their shapes from NetChain or NetGraph connectivity n n ports with default names and unspecified shapes {"name1","name2",…} explicit port names with unspecified shapes {shape1,shape2,…} default port names with specified shapes or encoders <"name1"shape1,… > explicit port names with specified shapes or encoders - Shape specifications for each port include:
-
"Real" a single real number "Integer" a single integer Restricted["Integer",n] an integer between 1 and n n a vector of length n {n1,n2,…} an array of dimensions n1×n2×… "Varying" a vector whose length is variable {"Varying",n2,n3,…} an array whose first dimension is variable and remaining dimensions are n2×n3×… NetEncoder[…] an encoder
Examples
open allclose allBasic Examples (1)
By default, multi-input layers such as ThreadingLayer have an undefined number of input ports:
Use InputPorts to create a ThreadingLayer with three ports having default names and unspecified shapes:
Scope (3)
Create a CatenateLayer with two inputs having explicit names and unspecified shapes:
Create a PlaceholderLayer with four inputs having default names and specified shapes:
Create a DotLayer with two inputs having explicit names and specified shapes:
Text
Wolfram Research (2020), InputPorts, Wolfram Language function, https://reference.wolfram.com/language/ref/InputPorts.html.
CMS
Wolfram Language. 2020. "InputPorts." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/InputPorts.html.
APA
Wolfram Language. (2020). InputPorts. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/InputPorts.html