Model size is often limited by the capabilities of the deployed hardware, or in relation to LSTMs the timing requirement. By using the singular value decomposition, the model can be compressed into a smaller size with presumably a shorter forward pass time. The reduced model will be smaller than the starting model, but still be composed of full matrices. Model reduction is done with the use of two types of regularziers: the Hoyer regularizer induces sparsity in the singular values while an orthogonality regularzier preserves orthogonality in the left and right eigenmatrices.
This repository has been archived by the owner on Oct 26, 2022. It is now read-only.
dncoble/LSTM-acceleration-with-singular-value-decomposition
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
A project for my linear algebra class, this is an extension of my work in dncoble/LSTM-State-Estimation-with-Time-Domain-Signal and dncoble/LSTM-implementation-on-FPGA
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published