nn.conv2d strides

nn.conv2d中的strides参数指定了卷积核在输入数据上的滑动步长。在引用的代码中，conv1的strides为[1,1,1,1]，conv2的strides为[1,2,2,1]，conv3的strides为[1,3,3,1]，conv4的strides为[1,4,4,1]。这意味着在conv1中，卷积核每次在输入数据上以1个像素的步长进行滑动，而在conv2中，卷积核每次在输入数据上以2个像素的步长进行滑动，以此类推。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* [Tensorflow 卷积神经网络 tf.nn.conv2d函数的strides参数理解](https://blog.csdn.net/qq_28632639/article/details/86588843)[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_1"}}] [.reference_item style="max-width: 50%"]
- *2* *3* [tf.nn.conv2d()函数详解(strides与padding的关系)](https://blog.csdn.net/tuying_001/article/details/103617727)[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_1"}}] [.reference_item style="max-width: 50%"]
[ .reference_list ]