使用全新且更新的 torchinfo。

在 PyTorch 中实现 Keras 风格的 model.summary()

Keras 提供了一个简洁的 API，可以查看模型的可视化结构，在调试网络时非常有用。以下是一个基础代码示例，用于在 PyTorch 中模拟类似的功能。其目标是提供补充信息，弥补 PyTorch 中 print(your_model) 所无法提供的内容。

使用方法

• pip install torchsummary 或
• git clone https://github.com/sksq96/pytorch-summary

from torchsummary import summary
summary(your_model, input_size=(channels, H, W))

• 请注意，input_size 是必需的，以便在网络中执行一次前向传播。

示例

用于 MNIST 数据集的 CNN

import torch
import torch.nn as nn
import torch.nn.functional as F
from torchsummary import summary

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # PyTorch v0.4.0
model = Net().to(device)

summary(model, (1, 28, 28))

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1           [-1, 10, 24, 24]             260
            Conv2d-2             [-1, 20, 8, 8]           5,020
         Dropout2d-3             [-1, 20, 8, 8]               0
            Linear-4                   [-1, 50]          16,050
            Linear-5                   [-1, 10]             510
================================================================
Total params: 21,840
Trainable params: 21,840
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.00
Forward/backward pass size (MB): 0.06
Params size (MB): 0.08
Estimated Total Size (MB): 0.15
----------------------------------------------------------------

VGG16

import torch
from torchvision import models
from torchsummary import summary

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
vgg = models.vgg16().to(device)

summary(vgg, (3, 224, 224))

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1         [-1, 64, 224, 224]           1,792
              ReLU-2         [-1, 64, 224, 224]               0
            Conv2d-3         [-1, 64, 224, 224]          36,928
              ReLU-4         [-1, 64, 224, 224]               0
         MaxPool2d-5         [-1, 64, 112, 112]               0
            Conv2d-6        [-1, 128, 112, 112]          73,856
              ReLU-7        [-1, 128, 112, 112]               0
            Conv2d-8        [-1, 128, 112, 112]         147,584
              ReLU-9        [-1, 128, 112, 112]               0
        MaxPool2d-10          [-1, 128, 56, 56]               0
           Conv2d-11          [-1, 256, 56, 56]         295,168
             ReLU-12          [-1, 256, 56, 56]               0
           Conv2d-13          [-1, 256, 56, 56]         590,080
             ReLU-14          [-1, 256, 56, 56]               0
           Conv2d-15          [-1, 256, 56, 56]         590,080
             ReLU-16          [-1, 256, 56, 56]               0
        MaxPool2d-17          [-1, 256, 28, 28]               0
           Conv2d-18          [-1, 512, 28, 28]       1,180,160
             ReLU-19          [-1, 512, 28, 28]               0
           Conv2d-20          [-1, 512, 28, 28]       2,359,808
             ReLU-21          [-1, 512, 28, 28]               0
           Conv2d-22          [-1, 512, 28, 28]       2,359,808
             ReLU-23          [-1, 512, 28, 28]               0
        MaxPool2d-24          [-1, 512, 14, 14]               0
           Conv2d-25          [-1, 512, 14, 14]       2,359,808
             ReLU-26          [-1, 512, 14, 14]               0
           Conv2d-27          [-1, 512, 14, 14]       2,359,808
             ReLU-28          [-1, 512, 14, 14]               0
           Conv2d-29          [-1, 512, 14, 14]       2,359,808
             ReLU-30          [-1, 512, 14, 14]               0
        MaxPool2d-31            [-1, 512, 7, 7]               0
           Linear-32                 [-1, 4096]     102,764,544
             ReLU-33                 [-1, 4096]               0
          Dropout-34                 [-1, 4096]               0
           Linear-35                 [-1, 4096]      16,781,312
             ReLU-36                 [-1, 4096]               0
          Dropout-37                 [-1, 4096]               0
           Linear-38                 [-1, 1000]       4,097,000
================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 218.59
Params size (MB): 527.79
Estimated Total Size (MB): 746.96
----------------------------------------------------------------

多输入

import torch
import torch.nn as nn
from torchsummary import summary

class SimpleConv(nn.Module):
    def __init__(self):
        super(SimpleConv, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(1, 1, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
        )

    def forward(self, x, y):
        x1 = self.features(x)
        x2 = self.features(y)
        return x1, x2
    
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = SimpleConv().to(device)

summary(model, [(1, 16, 16), (1, 28, 28)])

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1            [-1, 1, 16, 16]              10
              ReLU-2            [-1, 1, 16, 16]               0
            Conv2d-3            [-1, 1, 28, 28]              10
              ReLU-4            [-1, 1, 28, 28]               0
================================================================
Total params: 20
Trainable params: 20
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.77
Forward/backward pass size (MB): 0.02
Params size (MB): 0.00
Estimated Total Size (MB): 0.78
----------------------------------------------------------------

参考文献

• 本包的灵感来源于 PyTorch 的这个 issue。
• 感谢 @ncullen93 和 @HTLife。
• 模型大小估算部分由 @jacobkimmel 贡献（详情见此处）。

许可证

pytorch-summary 采用 MIT 许可证。

pytorch-summary 快速上手指南

pytorch-summary 是一个为 PyTorch 设计的轻量级工具，旨在提供类似 Keras model.summary() 的功能。它能清晰地展示模型的层级结构、输出形状、参数量以及内存占用估算，是调试和评估神经网络结构的得力助手。

注意：原作者推荐新项目 torchinfo，但 pytorch-summary 依然稳定可用且简洁。

环境准备

• 系统要求：支持 Linux、macOS 或 Windows。
• 前置依赖：
  • Python 3.6+
  • PyTorch (建议版本 >= 0.4.0)
  • 可选：CUDA（如需在 GPU 上运行模型分析）

安装步骤

你可以通过 PyPI 直接安装，或从 GitHub 克隆源码。国内开发者推荐使用清华源加速安装。

方式一：使用 pip 安装（推荐）

pip install torchsummary -i https://pypi.tuna.tsinghua.edu.cn/simple

方式二：从 GitHub 克隆

git clone https://github.com/sksq96/pytorch-summary
cd pytorch-summary
pip install .

基本使用

使用该工具的核心只需两步：导入 summary 函数，并传入模型实例与输入尺寸元组。

核心代码示例：

from torchsummary import summary
summary(your_model, input_size=(channels, H, W))

关键点：input_size 参数是必须的，工具需要利用它执行一次前向传播以推导各层输出形状。

完整示例（MNIST CNN 模型）：

import torch
import torch.nn as nn
import torch.nn.functional as F
from torchsummary import summary

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2(x), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

# 自动检测设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = Net().to(device)

# 生成摘要：输入为单通道 28x28 图像
summary(model, (1, 28, 28))

输出效果预览：

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1           [-1, 10, 24, 24]             260
            Conv2d-2             [-1, 20, 8, 8]           5,020
            Linear-3                   [-1, 50]          16,050
            Linear-4                   [-1, 10]             510
================================================================
Total params: 21,840
Trainable params: 21,840
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.00
Forward/backward pass size (MB): 0.06
Params size (MB): 0.08
Estimated Total Size (MB): 0.15
----------------------------------------------------------------

该输出包含了每一层的类型、输出张量形状、参数量，以及模型整体的内存占用估算，帮助你快速把握模型规模。