PyTorch中model.modules()返回的module含义及Sequential与单层模块共存原因的技术咨询
2026-4-30
Understanding
model.modules() in PyTorch Code Example
from torchvision import models model = models.vgg16(pretrained=True).features for i, module in enumerate(model.modules()): print('-' * 60) print(type(module)) print(module)
Answers to Your Questions
1. What exactly does module in model.modules() refer to?
As the official docs note, modules() returns an iterator over all modules in the network—and here's the core point: in PyTorch, every component of a neural network (whether it's a single layer or a group of layers) inherits from the nn.Module class.
So each module in your loop is a distinct nn.Module instance from anywhere in the model's hierarchy. It could be the top-level Sequential container holding all layers, a single Conv2d convolution layer, a ReLU activation function, or even a nested container if your model had deeper structure.
2. Why does torch.nn.modules.container.Sequential appear alongside individual layers like Conv2d/ReLU?
This is all about how modules() traverses the model—it does a recursive walk of the entire structure. Let's break down what's happening with your VGG16 features module:
- The
modelvariable here is a top-level Sequential container that wraps all the Conv2d, ReLU, and MaxPool2d layers in order. - When you call
model.modules(), it first returns the top-level Sequential itself (which is why that's the first block in your output). - Then it recursively dives into that Sequential, iterating over every sub-module inside it. Each Conv2d, ReLU, and MaxPool2d is a sub-module of the Sequential, so they get returned next in the iterator.
This recursive behavior ensures you can access every single module in your model, no matter how they're nested together.
Sample Output
------------------------------------------------------------ <class 'torch.nn.modules.container.Sequential'> Sequential( (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): ReLU(inplace=True) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): ReLU(inplace=True) (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (6): ReLU(inplace=True) (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (8): ReLU(inplace=True) (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (11): ReLU(inplace=True) (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (13): ReLU(inplace=True) (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (15): ReLU(inplace=True) (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (18): ReLU(inplace=True) (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (20): ReLU(inplace=True) (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (22): ReLU(inplace=True) (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (25): ReLU(inplace=True) (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (27): ReLU(inplace=True) (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (29): ReLU(inplace=True) (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.pooling.MaxPool2d'> MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.pooling.MaxPool2d'> MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.pooling.MaxPool2d'> MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.pooling.MaxPool2d'> MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.conv.Conv2d'> Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ------------------------------------------------------------ <class 'torch.nn.modules.activation.ReLU'> ReLU(inplace=True) ------------------------------------------------------------ <class 'torch.nn.modules.pooling.MaxPool2d'> MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
内容的提问来源于stack exchange，提问作者mrgloom
