efficientnet-rethinking-model-scaling-for-convolutional-neural-networks-2022-017

Mingxing Tan, Quoc V. Le

0 Est. reading time25 views0 downloads0 reviews

Verified repository recordMetadataMetadata 90%Repository readiness 92%

efficientnet-rethinking-model-scaling-for-convolutional-neural-networks-2022-017

Mingxing Tan, Quoc V. LeUFTAN UNIVERSITYComputer Engineering2022

Abstract

This record links to the EfficientNet paper, which proposes compound scaling for convolutional neural network depth, width, and resolution. It supports realistic testing of undergraduate AI project metadata and external PDF handling.

Metadata

Author: Mingxing Tan, Quoc V. Le
Supervisor: Dr. Ngozi A. Okeke
Faculty: Engineering
Department: Computer Engineering
Document type: Final Year Project
Year: 2022
Keywords: EfficientNet, model scaling, convolutional neural networks, image classification, neural architecture search
Access: Metadata
License: all_rights_reserved

Cite this work

Auto-generated from the record metadata: authors, journal title, DOI, volume, issue/serial, pages and publication date. Review before final academic use.

Mingxing Tan, Quoc V. Le (2026). efficientnet-rethinking-model-scaling-for-convolutional-neural-networks-2022-017 [Final Year Project]. UFTAN UNIVERSITY. https://inrepscholar.com/uftan-university/projects/956

Source fields used: Mingxing Tan, Quoc V. Le

Export citation and metadata

APA RIS BibTeX Dublin Core DataCite

Academic reviews

No approved reviews yetReviews and citation feedback appear here after moderation.

Sign in to submit a review or correction suggestion for this record.

efficientnet-rethinking-model-scaling-for-convolutional-neural-networks-2022-017

Abstract

Metadata

Cite this work

Academic reviews

Related records