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

Many mission-critical systems are based on GPU for inference. It requires notonly high recognition accuracy but also low latency in responding time.Although many studies are devoted to optimizing the structure of deep modelsfor efficient inference, most of them do not leverage the architecture of\textbf{modern GPU} for fast inference, leading to suboptimal performance. Toaddress this issue, we propose a general principle for designing GPU-efficientnetworks based on extensive empirical studies. This design principle enables usto search for GPU-efficient network structures effectively by a simple andlightweight method as opposed to most Neural Architecture Search (NAS) methodsthat are complicated and computationally expensive. Based on the proposedframework, we design a family of GPU-Efficient Networks, or GENets in short. Wedid extensive evaluations on multiple GPU platforms and inference engines.While achieving $\geq 81.3\%$ top-1 accuracy on ImageNet, GENet is up to $6.4$times faster than EfficienNet on GPU. It also outperforms most state-of-the-artmodels that are more efficient than EfficientNet in high precision regimes. Oursource code and pre-trained models are available from\url{https://github.com/idstcv/GPU-Efficient-Networks}.

Neural Architecture Design for GPU-Efficient Networks