Machine learningCNN architectures
Inception Network（GoogLeNet）
Inception Network，由Google的Szegedy等人于2015年提出并以GoogLeNet的名称提交给CVPR，是一个22层的深度卷积神经网络，专为大规模图像识别而设计。其核心贡献是Inception模块，该模块并行应用多种卷积核尺寸的卷积，并将其输出连接起来，使网络能够在不显著增加计算成本的情况下同时捕获不同尺度的空间特征。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Szegedy, C., et al. (2015). Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1–9. DOI: 10.1109/CVPR.2015.7298594 ↗
如何引用本页
ScholarGate. (2026, June 2). Inception / GoogLeNet. ScholarGate. https://scholargate.app/zh/deep-learning/inception-network
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →