tinybig.head
RPN Heads
In this module, we implement several frequently used RPN head that can be used to design and construct the RPN based function learning models.
The heads implemented in this module all inherit from the tinybig.module.base_head.head class. For most of the heads, they will only re-define the init method to provide the component functions. Meanwhile, for some of the heads, they will also implement some other methods to re-define the internal calculation process, which will be clearly specified in the class implementation.
Classes in this Module
This module contains the following categories of component heads:
- Basic heads
- Grid based heads
- Chain based heads
- Graph based heads
- Bilinear heads
Organization of this Module
RPN Head
- base_head (defined in the tinybig.module directory)