keras_input() is a Keras function that creates a symbolic input tensor specifying the shape and data type accepted by a model.
Input is a symbolic tensor created by keras_input(). It specifies the shape and data type that a model will accept, without containing actual data. section 7.2.2
An Input object:
Accepts layers as operations; each layer returns another symbolic tensor with updated shape and dtype information. section 7.2.2
How Deep Learning with R, Third Edition covers it
How deep it goes
Explains symbolic metadata and layer connections, stopping short of actual data processing.
Examples
Uses a three-feature Dense model and a ticket classifier with title, body, and tag inputs.
What it assumes
Assumes layers and tensors as nearby concepts while making symbolic input specifications explicit.
What you can do after
Build it from scratch by declaring model inputs and connecting them to layers and outputs.
How it connects
Connects symbolic tensors with layers, Functional API graphs, model inputs, and multiple-input models.
symbolic tensorproduces · A symbolic tensor is a tensor-like placeholder that specifies shape and data type without containing actual data values.
generationconfigures · Generation is the computational production of outputs from supplied inputs or context, often by applying a model to produce predictions or new content.
inputkind of · An input is a value, information, or signal supplied to a system, computation, or interface for processing or to influence its behavior.
This explainer was generated by Manning's knowledge graph from the text of Deep Learning with R, Third Edition. The section links point to the parts of the book it draws on.
