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 3 × 3 convolution and ReLU, while the training-time model has a multi-branch topology. Such decoupling of the training-time and inference-time architecture is realized by a structural re-parameterization technique so that the model is named RepVGG. On ImageNet, RepVGG reaches over 80% top-1 accuracy, which is the first time for a plain model, to the best of our knowledge. On NVIDIA 1080Ti GPU, RepVGG models run 83% faster than ResNet-50 or 101% faster than ResNet-101 with higher accuracy and show favorable accuracy-speed trade-off compared to the state-of-the-art models like EfficientNet and RegNet. The code and trained models are available at https://github.com/megvii-model/RepVGG.

1. Introduction

A classic Convolutional Neural Network (ConvNet), VGG [31], achieved huge success in image recognition with a simple architecture composed of a stack of conv, ReLU, and pooling. With Inception [33], [34], [32], [19], ResNet [12] and DenseNet [17], a lot of research interests were shifted to well-designed architectures, making the models more and more complicated. Some recent architectures are based on automatic [44], [29], [23] or manual [28] architecture search, or a searched compound scaling strategy [35].