DSC深度可分离卷积

DSC，即深度可分离卷积(Depthwise Separable Convolution)，是一种卷积神经网络的计算方式。它将传统的卷积操作分解为两个步骤：Depthwise的逐通道卷积和Pointwise的逐点卷积。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *2* *3* [(八)深度可分离卷积(Depthwise Separable Convolution，DSC)](https://blog.csdn.net/lx_ros/article/details/127293543)[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: 100%"]
[ .reference_list ]