resnet的演化(res2net,resnext,se-resnet,sk-resnet,resnest) 1. 总体演化过程 演化方向主要为两种: split-transform-merge、squeeze-and-attention。 split-transform-merge:通过卷积的可分离性质,增加网络宽度,从而在不增加算力的情况下增加网络的表征能力(不同维度通道特征的融合)。 squ... ...
In this paper, the cattle face images are obtained from different angles to generate the cow face dataset, and a cow face recognition model based on SK_ResNet is proposed. Based on ResNet-50 and using a different number of sk_Bottleneck, this model integrates multiple receptive fields of ...
迁移学习差异对齐损失针对传统深度学习模型在变工况环境下泛化能力差,诊断精度低的问题,提出了一种基于SK-ResNet和迁移学习的滚动轴承故障诊断方法.首先,对采集到的时域信号进行快速傅里叶变换(FFT)获得频域信号,并进行加权融合得到新的时频域数据集;其次,将选择性内核网络(SKNet)融入到残差网络(ResNet)中提高特征提...
In this paper, we design a hybrid SKResNet-TCN network model based on these two networks, and propose a solution of hybrid inflated convolution for the problem of losing information between data features in inflated convolution, using adaptive maximum pooling to preserve signific...