哪些 PyTorch 模块受 model.eval() 和 model.train() 影响? [英] Which PyTorch modules are affected by model.eval() and model.train()?

问题描述

model.eval() 方法修改某些模块(层)，这些模块(层)在训练和推理期间需要以不同的方式表现.文档中列出了一些示例:

The model.eval() method modifies certain modules (layers) which are required to behave differently during training and inference. Some examples are listed in the docs:

这仅对某些模块有 [an] 影响.如果它们受到影响，请参阅特定模块的文档以了解其在培训/评估模式下的行为的详细信息，例如Dropout、BatchNorm 等

This has [an] effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

是否有一份详细的清单，列出了哪些模块受到影响?

Is there an exhaustive list of which modules are affected?

推荐答案

除了 @iacob 提供的信息:

<头>

基类	模块	标准
RNNBase	RNN LSTM GRU	dropout >0(默认:0)
变压器层	变压器 变压器编码器 变压器解码器	dropout >0 (Transformer 默认:0.1)
懒惰变体	LazyBatchNorm 目前每晚 合并 PR	track_running_stats=True

Base class	Module	Criteria
RNNBase	RNN LSTM GRU	dropout > 0 (default: 0)
Transformer layers	Transformer TransformerEncoder TransformerDecoder	dropout > 0 (Transformer default: 0.1)
Lazy variants	LazyBatchNorm currently nightly merged PR	track_running_stats=True

这篇关于哪些 PyTorch 模块受 model.eval() 和 model.train() 影响?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！