OutputPorts
is an option to specify the number, names or shapes of output ports for some neural net layers.
Details
- OutputPorts is typically used in PlaceholderLayer.
- Typical settings for OutputPorts 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×… NetDecoder[…] a decoder
Examples
open all close allBasic Examples (1)
By default, PlaceholderLayer has a single output port:
Use OutputPorts to create a PlaceholderLayer with three ports having default names and unspecified shapes:
Scope (3)
Create a PlaceholderLayer with two outputs having explicit names and unspecified shapes:
Create a PlaceholderLayer with four outputs having default names and specified shapes:
Create a PlaceholderLayer with two outputs having explicit names and specified shapes:
Text
Wolfram Research (2020), OutputPorts, Wolfram Language function, https://reference.wolfram.com/language/ref/OutputPorts.html.
CMS
Wolfram Language. 2020. "OutputPorts." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/OutputPorts.html.
APA
Wolfram Language. (2020). OutputPorts. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/OutputPorts.html