EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design
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.
Code (1)
Tasks
GPUobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
RepVGG: Making VGG-style ConvNets Great Again
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 SegmentationRepVGG-GELAN: Enhanced GELAN with VGG-STYLE ConvNets for Brain Tumour Detection
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 DetectionDetection of Small Targets in Sea Clutter Based on RepVGG and Continuous Wavelet Transform
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
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 SegmentationFast-ParC: Capturing Position Aware Global Feature for ConvNets and ViTs
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