Symbolic tensor
A symbolic tensor is a tensor-like placeholder that specifies shape and data type without containing actual data values.
Deep Learning with R, Third Edition
A symbolic tensor is a tensor-like object that encodes the shape and data type of future data without containing actual data values.
- How it is used
- Uses symbolic tensors to assemble Keras Functional computation graphs before supplying training or inference data.
- How deep it goes
- Defines symbolic tensors, demonstrates shape and dtype propagation, and distinguishes them from eager tensors during dataset tracing.
- Examples
- Demonstrates two Dense layers, a multi-input ticket classifier, intermediate-feature reuse, and image-segmentation dataset tracing.
- What you can do after
- Builds Functional Keras models, inspect their symbolic shapes and connections, and distinguish traced pipeline values from concrete examples.
Read how Deep Learning with R, Third Edition explains symbolic tensor →
Deep Learning with Python, Third Edition
A tensor-like placeholder that encodes shape and dtype information without holding actual data values.
- How it is used
- Represents future data while constructing Keras Functional API model graphs.
- How deep it goes
- Defines shape and dtype propagation through layers, but does not contain or process actual data values.
- Examples
- Uses keras.Input, Dense layers, shape inspection, and a two-layer Functional model.
- What you can do after
- Build it from scratch by connecting Keras layers and declaring model inputs and outputs.
Read how Deep Learning with Python, Third Edition explains symbolic tensor →
Related concepts
- dataset_mapused by · dataset_map is a dataset transformation method that applies a callable transformation to each dataset element.
- Inputproduced by · Input is a Keras constructor that creates a symbolic tensor specifying the shape and data type accepted by a model.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.