Graphcore C2 Card performance for image-based deep learning application: A Report

Qwant

Ilyes Kacher, Maxime Portaz, Hicham Randrianarivo, Sylvain Peyronnet

英文摘要：

Recently, Graphcore has introduced an IPU Processor for accelerating machine learning applications. The architecture of the processor has been designed to achieve state of the art performance on current machine intelligence models for both training and inference. In this paper, we report on a benchmark in which we have evaluated the performance of IPU processors on deep neural networks for inference. We focus on deep vision models such as ResNeXt. We report the observed latency, throughput and energy efficiency.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Checkup2Action：面向患者行动的多模态临床检查报告数据集

Checkup2Action: A Multimodal Clinical Check-up Report Dataset for Patient-Oriented Action Card Generation

Durham University（杜伦大学）；University of Oxford（牛津大学）

本文提出Checkup2Action数据集，用于生成结构化的行动卡，通过多模态检查报告生成患者导向的行动建议，评估行动的准确性、优先级和安全性。

2026-08-25cs.CLcs.CV

心血管磁共振成像的多模态表示学习

Multimodal Representation Learning of Cardiovascular Magnetic Resonance Imaging

Carnegie Mellon University（卡内基梅隆大学）；Cleveland Clinic（克利夫兰诊所）；CJ AI Center（CJ人工智能中心）

本文提出多模态学习框架 CMRformer，联合学习 CMR 图像序列与医生报告，并收集包含 13,787 项检查的大型数据集，在图像检索、报告检索和疾病分类等临床任务中取得显著性能。

2023-04-16cs.CV

基于心电图与临床报告多模态学习的心血管记录自动检索

Automated Cardiovascular Record Retrieval by Multimodal Learning between Electrocardiogram and Clinical Report

Carnegie Mellon University（卡内基梅隆大学）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Allegheny Health Network（阿勒格尼健康网络）；University of Colorado Denver（科罗拉多大学丹佛分校）

本研究针对现有ECG自动解读仅关注分类回归任务、忽略临床诊断报告的问题，结合LLMs与ViT模型，采用视觉-语言学习范式实现基于ECG图像的相似临床病例检索，为欠发达地区临床诊断提供支持。

2023-11-06cs.CVeess.SP

An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation

ETH Zurich（苏黎世联邦理工学院）

Accurate segmentation of the heart is an important step towards evaluating cardiac function. In this paper, we present a fully automated framework for segmentation of the left (LV) and right (RV) ventricular cavities and the myocardium (Myo) on short-axis cardiac MR images. We investigate various 2D and 3D convolutional neural network architectures for this task. We investigate the suitability of various state-of-the art 2D and 3D convolutional neural network architectures, as well as slight modifications thereof, for this task. Experiments were performed on the ACDC 2017 challenge training da…

2017-10-10cs.CV

基于深度学习和非对比心脏CT图像预测冠状动脉钙化严重程度

Predicting Coronary Artery Calcium Severity based on Non-Contrast Cardiac CT images using Deep Learning

School of Clinical Medicine, Faculty of Medicine \& Health, UNSW Sydney, Australia Rural Clinical School, Faculty of Medicine \& Health, UNSW, Port Macquarie, Australia School of Computer Science；Engineering, Faculty of Engineering, UNSW Sydney, Australia Bankstown-Lidcombe Hospital, South Western Sydney Local Health District, Bankstown, Australia

本研究开发了一种深度学习CNN模型，可将心脏非对比CT图像中的冠状动脉钙化评分分为六个临床类别，在68例患者数据上实现了96.5%的准确率和0.962的Cohen's kappa值，证明了其可行性和泛化能力。

2025-11-10cs.CV

CHMMOTv1——用于地中海贫血患者铁过载的心脏和肝脏多回波（T2*）MRI图像与临床数据集

CHMMOTv1 -- Cardiac and Hepatic Multi-Echo (T2*) MRI Images and Clinical Dataset for Iron Overload on Thalassemia Patients

Isfahan University of Medical Sciences（伊斯法罕医科大学）；Islamic Azad University Science and Research Branch（伊斯兰阿扎德大学科学研究分支）；Tehran University of Medical Sciences（德黑兰医科大学）

针对地中海贫血铁过载诊断资源匮乏问题，本文发布了CHMMOTv1数据集，包含124名患者的心脏和肝脏多回波T2* MRI图像及多项临床检验结果，以支持深度学习在医学诊断中的应用。

2023-05-17cs.CVeess.IV