SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.13630 · 2020

TResNet: High Performance GPU-Dedicated Architecture

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Many deep learning models, developed in recent years, reach higher ImageNet accuracy than ResNet50, with fewer or comparable FLOPS count. While FLOPs are often seen as a proxy for network efficiency, when measuring actual GPU training and inference throughput, vanilla ResNet50 is usually significantly faster than its recent competitors, offering better throughput-accuracy trade-off. In this work, we introduce a series of architecture modifications that aim to boost neural networks' accuracy, while retaining their GPU training and inference efficiency. We first demonstrate and discuss the bottlenecks induced by FLOPs-optimizations. We then suggest alternative designs that better utilize GPU structure and assets. Finally, we introduce a new family of GPU-dedicated models, called TResNet, which achieve better accuracy and efficiency than previous ConvNets. Using a TResNet model, with similar GPU throughput to ResNet50, we reach 80.8 top-1 accuracy on ImageNet. Our TResNet models also transfer well and achieve state-of-the-art accuracy on competitive single-label classification datasets such as Stanford cars (96.0%), CIFAR-10 (99.0%), CIFAR-100 (91.5%) and Oxford-Flowers (99.1%). They also perform well on multi-label classification and object detection tasks. Implementation is available at: https://github.com/mrT23/TResNet.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.13630")
get_code_for_paper("2003.13630")
have("2003.13630")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2003.13630.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2003.13630.svg)](https://syntology.ai/paper/2003.13630)

Connect an agent — have() is free.