transformer网络图

transformer网络结构如下图所示：

注意！！！！！！！！！！transformer的输入是有两个的，一个在Encoder，一个在Decoder（机器翻译是这样）。该网络结构包括编码端和解码端的输入。另外，在计算机视觉领域，还有一些与图神经网络和图变换器相关的研究。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *2* [Transformer](https://blog.csdn.net/a264672/article/details/121548092)[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* [当图网络遇上计算机视觉！计算机视觉中基于图神经网络和图Transformer的方法和最新进展...](https://blog.csdn.net/amusi1994/article/details/127116547)[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 ]