Experiencing Rapid Prototyping of Machine Learning Based Multimedia Applications in Rapsai
Informations
Type:
inproceedings
Auteurs:
Du, Ruofei and Li, Na and Jin, Jing and Carney, Michelle and Yuan, Xiuxiu and Iyengar, Ram and Yu, P...
Pertinence:
Moyenne
Référence:
Doi:
10.1145/3544549.3583925
Mots-clés:
deep neural networks, visual analytics, data augmentation, model comparison, visual programming, dee...
Url:
https://doi.org/10.1145/3544549.3583925
Date de publication:
04/2023
Résumé:
programmation visuelle d'application. diagrammes de flux. Différents types de noeuds (input, effect, model, output...).
Abstract:
We demonstrate Rapsai, a visual programming platform that aims to streamline the rapid and iterative development of end-to-end machine learning (ML)-based multimedia applications. Rapsai features a node-graph editor that enables interactive characterization and visualization of ML model performance, which facilitates the understanding of how the model behaves in different scenarios. Moreover, the platform streamlines end-to-end prototyping by providing interactive data augmentation and model comparison capabilities within a no-coding environment. Our demonstration showcases the versatility of Rapsai through several use cases, including virtual background, visual effects with depth estimation, and audio denoising. The implementation of Rapsai is intended to support ML practitioners in streamlining their workflow, making data-driven decisions, and comprehensively evaluating model behavior with real-world input.
Pdf:
Lien pdf
Références
1 articles
Titre Type Pertinence Auteurs Date Publication Références Citations Actions
AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompt... inproceedings Haute Wu, Tongshuang and Terry, Michael and Cai, Carrie Jun 04/2022 0 3
Citations
0 articles
Titre Type Pertinence Auteurs Date Publication Références Citations Actions
Pas encore d'article
Mots-clés
7 mots-clés
Nom Nombre d'articles Actions
visual analytics 1
visual programming 1
deep neural networks 1
model comparison 1
node-graph editor 1
data augmentation 1
deep learning 1
Auteurs
10 auteurs
Nom Nombre d'articles Actions
Ruofei and Li 1
Adarsh and Olwal 1
Michelle and Yuan 1
Du 1
Ping and Kowdle 1
Jing and Carney 1
Ram and Yu 1
Na and Jin 1
Alex 1
Xiuxiu and Iyengar 1