"scheduler": "steplr"

"scheduler": "steplr"是指使用StepLR调度器对学习率进行调整。StepLR是PyTorch中的一个学习率调度器，它会在训练过程中按照预定的步长进行学习率的衰减。在给定的步数之后，学习率会按照给定的因子进行衰减。这个调度器可以通过设置lr_period和lr_decay来调节学习率的衰减周期和衰减因子。该调度器的使用方式为torch.optim.lr_scheduler.StepLR(optimizer, step_size, gamma)。其中，optimizer是优化器对象，step_size表示每隔多少个epoch调整一次学习率，gamma表示学习率的衰减因子。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *3* [[pytorch] torch.optimizer.lr_scheduler调整学习率](https://blog.csdn.net/weixin_43844219/article/details/104319339)[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* [torch.optim.lr_scheduler.StepLR参数解析](https://blog.csdn.net/jjw_zyfx/article/details/120422398)[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 ]