nn.BatchNorm2d(16, affine=False)

nn.BatchNorm2d(16, affine=False)是一个批量归一化层，其中16是输入特征的数量，affine=False表示不添加可学习的仿射变换参数。在这种情况下，γ=1，β=0，并且不能学习被更新。这意味着批量归一化层不会对输入进行缩放和平移操作，只进行标准化处理。\[1\]\[2\]
#### 引用[.reference_title]
- *1* [PyTorch】详解nn模块的BatchNorm2d()函数](https://blog.csdn.net/qq_45368632/article/details/124209629)[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^v91^insertT0,239^v3^insert_chatgpt"}} ] [.reference_item]
- *2* [pytorch中nn.BatchNorm2d函数的使用](https://blog.csdn.net/weixin_44656547/article/details/113409138)[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^v91^insertT0,239^v3^insert_chatgpt"}} ] [.reference_item]
- *3* [常见的类 nn.Conv2d，nn.BatchNorm2D，nn.AdaptiveAvgPool2d](https://blog.csdn.net/xiaoyuting999/article/details/129800756)[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^v91^insertT0,239^v3^insert_chatgpt"}} ] [.reference_item]
[ .reference_list ]