English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Much recent research has been dedicated to improving the efficiency oftraining and inference for image classification. This effort has commonlyfocused on explicitly improving theoretical efficiency, often measured asImageNet validation accuracy per FLOP. These theoretical savings have, however,proven challenging to achieve in practice, particularly on high-performancetraining accelerators.  In this work, we focus on improving the practical efficiency of thestate-of-the-art EfficientNet models on a new class of accelerator, theGraphcore IPU. We do this by extending this family of models in the followingways: (i) generalising depthwise convolutions to group convolutions; (ii)adding proxy-normalized activations to match batch normalization performancewith batch-independent statistics; (iii) reducing compute by lowering thetraining resolution and inexpensively fine-tuning at higher resolution. We findthat these three methods improve the practical efficiency for both training andinference. Code available athttps://github.com/graphcore/graphcore-research/tree/main/Making_EfficientNet_More_Efficient .

Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training