ImageNet pre-trained models with batch normalization
ImageNet pre-trained models with batch normalization
复制标题
DOI：
--
复制
发表时间：
2016-12
期刊：
影响因子：
--
通讯作者：
Marcel Simon;E. Rodner;Joachim Denzler
中科院分区：
文献类型：
--
作者：
Marcel Simon;E. Rodner;Joachim Denzler
在ImageNet上预训练的卷积神经网络（CNN）是大多数最先进的方法的支柱。在本文中，我们为Caffe框架提供了一组新的预训练模型，这些模型具有流行的最先进的架构。第一个版本包括残余网络（ResNets）与生成脚本以及AlexNet和VGG19的批处理规范化变体。所有模型都优于具有相同架构的先前模型。模型和训练代码可以在这个http URL和这个https URL上找到
Convolutional neural networks (CNN) pre-trained on ImageNet are the backbone of most state-of-the-art approaches. In this paper, we present a new set of pre-trained models with popular state-of-the-art architectures for the Caffe framework. The first release includes Residual Networks (ResNets) with generation script as well as the batch-normalization-variants of AlexNet and VGG19. All models outperform previous models with the same architecture. The models and training code are available at this http URL and this https URL