resneXt网络模型结构
时间: 2024-04-28 15:24:25 浏览: 102
ResNeXt是对ResNet的改进,其网络结构可以简单地通过将ResNet网络中的Block替换成使用组卷积的Block来搭建。 ResNeXt的原始论文发表于2017年的CVPR,该论文更新了Residual Block,并采用了split-transform-merge策略,即分组卷积,而无需像Inception一样设计复杂的结构。 ResNeXt的拓扑结构与ResNet一致,但对于GPU等硬件更友好,因此在训练时具有更快的速度。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* [ResNeXt网络详解并使用pytorch搭建模型](https://blog.csdn.net/STATEABC/article/details/123737390)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v92^chatsearchT3_1"}}] [.reference_item style="max-width: 50%"]
- *2* *3* [深度学习之图像分类(九)--ResNeXt 网络结构](https://blog.csdn.net/baidu_36913330/article/details/120057689)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v92^chatsearchT3_1"}}] [.reference_item style="max-width: 50%"]
[ .reference_list ]
阅读全文