lstm时间步长的含义
时间: 2023-09-14 16:09:55 浏览: 364
LSTM中timesteps的理解
5星 · 资源好评率100%
时间步长(time step)在LSTM(长短期记忆网络)中表示每个输入序列在时间上的间隔。它定义了在一个batch中,每次输入给模型的连续时间序列的长度。例如,如果batch_size为100且time_step为10,在第一次训练时,会使用前100个数据进行训练,并且每次给模型输入10个连续的时间序列数据。这意味着模型会认为每个值与其前面的10个值有关系。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* [DeepLearning之LSTM模型输入参数](https://blog.csdn.net/Chris9633/article/details/104411253)[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%"]
- *2* *3* [DeepLearning之LSTM模型输入参数:time_step, input_size, batch_size的理解](https://blog.csdn.net/weixin_42101836/article/details/104386371)[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 ]
阅读全文