The UniNAS framework: combining modules in arbitrarily complex configurations with argument trees

12/03/2021
by   Kevin Alexander Laube, et al.
0

Designing code to be simplistic yet to offer choice is a tightrope walk. Additional modules such as optimizers and data sets make a framework useful to a broader audience, but the added complexity quickly becomes a problem. Framework parameters may apply only to some modules but not others, be mutually exclusive or depend on each other, often in unclear ways. Even so, many frameworks are limited to a few specific use cases. This paper presents the underlying concept of UniNAS, a framework designed to incorporate a variety of Neural Architecture Search approaches. Since they differ in the number of optimizers and networks, hyper-parameter optimization, network designs, candidate operations, and more, a traditional approach can not solve the task. Instead, every module defines its own hyper-parameters and a local tree structure of module requirements. A configuration file specifies which modules are used, their used parameters, and which other modules they use in turn This concept of argument trees enables combining and reusing modules in complex configurations while avoiding many problems mentioned above. Argument trees can also be configured from a graphical user interface so that designing and changing experiments becomes possible without writing a single line of code. UniNAS is publicly available at https://github.com/cogsys-tuebingen/uninas

READ FULL TEXT

page 7

page 15

research
06/09/2022

Neural Prompt Search

The size of vision models has grown exponentially over the last few year...
research
04/22/2019

Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks

Recently, deep learning has become a de facto standard in machine learni...
research
11/08/2021

Triple-level Model Inferred Collaborative Network Architecture for Video Deraining

Video deraining is an important issue for outdoor vision systems and has...
research
05/27/2019

Structure Learning for Neural Module Networks

Neural Module Networks, originally proposed for the task of visual quest...
research
01/16/2018

GitGraph - Architecture Search Space Creation through Frequent Computational Subgraph Mining

The dramatic success of deep neural networks across multiple application...
research
12/24/2020

Union-net: A deep neural network model adapted to small data sets

In real applications, generally small data sets can be obtained. At pres...
research
04/18/2023

Neural Architecture Search for Visual Anomaly Segmentation

This paper presents AutoPatch, the first application of neural architect...

Please sign up or login with your details

Forgot password? Click here to reset