group convolution

Group convolution（分组卷积）是一种卷积运算的方法，它可以将输入的特征图分成多个组，并对每个组进行独立的卷积计算。在每个组内部，使用常规的卷积运算（也称为Depthwise Convolution）对特征图进行处理，然后再使用Pointwise Convolution对各个组的输出进行整合得到最终的特征图。这种分组的方式可以减少卷积运算的参数量，并且可以在参数量相同的情况下构建更深的神经网络。相比于传统的常规卷积，group convolution可以有效地减少参数数量，提高模型的效率和性能。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *2* [【 group convolution (分组卷积)详解】](https://blog.csdn.net/weixin_49117441/article/details/122648894)[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^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 50%"]
- *3* [dgconv.pytorch:动态分组卷积和可分组的ConvNet的PyTorch实施与预训练的G-ResNeXt模型](https://download.csdn.net/download/weixin_42133861/17819550)[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^v93^chatsearchT3_2"}}] [.reference_item style="max-width: 50%"]
[ .reference_list ]