paper-with-me

홈 › Papers

EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design

2023-02-01 · Kaiheng Weng, Xiangxiang Chu, Xiaoming Xu, Junshi Huang, Xiaoming Wei

We present a hardware-efficient architecture of convolutional neural network, which has a repvgg-like architecture. Flops or parameters are traditional metrics to evaluate the efficiency of networks which are not sensitive to hardware including computing ability and memory bandwidth. Thus, how to design a neural network to efficiently use the computing ability and memory bandwidth of hardware is a critical problem. This paper proposes a method how to design hardware-aware neural network. Based on this method, we designed EfficientRep series convolutional networks, which are high-computation hardware(e.g. GPU) friendly and applied in YOLOv6 object detection framework. YOLOv6 has published YOLOv6N/YOLOv6S/YOLOv6M/YOLOv6L models in v1 and v2 versions.

📄 PDF Abstract BibTeX arXiv:2302.00386

Code (1)

meituan/yolov6 공식 구현 pytorch

Tasks

GPUobject-detectionObject Detection

Similar Papers 제목 키워드 기반

RepVGG: Making VGG-style ConvNets Great Again

2021-01-11 · CVPR 2021 1 · Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han 외

We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and ReLU, while the training-time model has a mul…

GPUImage ClassificationSemantic Segmentation

RepVGG-GELAN: Enhanced GELAN with VGG-STYLE ConvNets for Brain Tumour Detection

2024-05-06 · Thennarasi Balakrishnan, Sandeep Singh Sengar

Object detection algorithms particularly those based on YOLO have demonstrated remarkable efficiency in balancing speed and accuracy. However, their application in brain tumour detection remains underexplored. This study…

Computational Efficiencyobject-detectionObject Detection

Detection of Small Targets in Sea Clutter Based on RepVGG and Continuous Wavelet Transform

2023-11-14 · Jingchen Ni, Haoru Li, Lilin Xu, Jing Liang

Constructing a high-performance target detector under the background of sea clutter is always necessary and important. In this work, we propose a RepVGGA0-CWT detector, where RepVGG is a residual network that gains a hig…

Make RepVGG Greater Again: A Quantization-aware Approach

2022-12-03 · Xiangxiang Chu, Liang Li, Bo Zhang

The tradeoff between performance and inference speed is critical for practical applications. Architecture reparameterization obtains better tradeoffs and it is becoming an increasingly popular ingredient in modern convol…

QuantizationSemantic Segmentation

Fast-ParC: Capturing Position Aware Global Feature for ConvNets and ViTs

2022-10-08 · Tao Yang, Haokui Zhang, Wenze Hu, Changwen Chen 외

Transformer models have made tremendous progress in various fields in recent years. In the field of computer vision, vision transformers (ViTs) also become strong alternatives to convolutional neural networks (ConvNets),…

image-classificationImage ClassificationInductive BiasPosition