EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design
This work addresses the need for hardware-efficient neural network design for applications like object detection, but it appears incremental as it builds on existing RepVGG-style architectures without claiming major breakthroughs.
The paper tackles the problem of designing neural networks that efficiently utilize hardware computing ability and memory bandwidth, proposing a hardware-aware method and applying it to create EfficientRep series convolutional networks, which are integrated into the YOLOv6 object detection framework with models like YOLOv6N/YOLOv6S/YOLOv6M/YOLOv6L.
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.