Pytorch基础及实战(5)——模型组网
在深度学习中，模型组网即是指设计和构建深度神经网络模型的过程。深度神经网络模型通常由多个层（Layer）组成，每个层都包含多个神经元（Neuron），并通过一定的连接方式进行信息传递和特征提取。
本文笔者将介绍模型组网的几种常见方法。
一、直接使用内置模型
Pytorch框架目前在 torchvision.models 下内置了计算机视觉领域的一些经典模型，只需几行代码即可完成网络构建和初始化，适合完成一些简单的深度学习任务，满足深度学习初阶用户感受模型的输入和输出形式、了解模型的性能。
import torchvision.models as models
model_names = sorted(
#遍历models模块中的所有属性名称
name for name in models.__dict__
# 对每个属性名称进行过滤，只保留名称全为小写字母、
# 不以双下划线开头且对应的属性值为可调用对象的属性名称
if name.islower() and not name.startswith("__")
and callable(models.__dict__[name]))
print('PyTorch框架内置模型：', model_names)
PyTorch框架内置模型： ['alexnet', 'convnext_base', 'convnext_large', 'convnext_small', 'convnext_tiny', 'densenet121','densenet161','densenet169', 'densenet201', 'efficientnet_b0', 'efficientnet_b1', 'efficientnet_b2', 'efficientnet_b3', 'efficientnet_b4', 'efficientnet_b5', 'efficientnet_b6', 'efficientnet_b7', 'efficientnet_v2_l', 'efficientnet_v2_m', 'efficientnet_v2_s', 'get_model', 'get_model_builder', 'get_model_weights', 'get_weight', 'googlenet', 'inception_v3', 'list_models', 'maxvit_t', 'mnasnet0_5', 'mnasnet0_75', 'mnasnet1_0', 'mnasnet1_3', 'mobilenet_v2', 'mobilenet_v3_large', 'mobilenet_v3_small', 'regnet_x_16gf', 'regnet_x_1_6gf', 'regnet_x_32gf', 'regnet_x_3_2gf', 'regnet_x_400mf', 'regnet_x_800mf', 'regnet_x_8gf', 'regnet_y_128gf', 'regnet_y_16gf', 'regnet_y_1_6gf', 'regnet_y_32gf', 'regnet_y_3_2gf', 'regnet_y_400mf', 'regnet_y_800mf', 'regnet_y_8gf', 'resnet101', 'resnet152', 'resnet18', 'resnet34', 'resnet50', 'resnext101_32x8d', 'resnext101_64x4d', 'resnext50_32x4d', 'shufflenet_v2_x0_5', 'shufflenet_v2_x1_0', 'shufflenet_v2_x1_5', 'shufflenet_v2_x2_0', 'squeezenet1_0', 'squeezenet1_1', 'swin_b', 'swin_s', 'swin_t', 'swin_v2_b', 'swin_v2_s', 'swin_v2_t', 'vgg11', 'vgg11_bn', 'vgg13', 'vgg13_bn', 'vgg16', 'vgg16_bn', 'vgg19', 'vgg19_bn', 'vit_b_16', 'vit_b_32', 'vit_h_14', 'vit_l_16', 'vit_l_32', 'wide_resnet101_2', 'wide_resnet50_2']
以resnet18为例，可通过如下代码组网：
import torch
import torchvision.models as models
from torchsummary import summary
# 获取resnet18模型
model = models.resnet18()
# 打印模型结构和参数数量等信息
summary(model, (3, 224, 224))
'''
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 112, 112] 9,408
BatchNorm2d-2 [-1, 64, 112, 112] 128
ReLU-3 [-1, 64, 112, 112] 0
MaxPool2d-4 [-1, 64, 56, 56] 0
Conv2d-5 [-1, 64, 56, 56] 36,864
BatchNorm2d-6 [-1, 64, 56, 56] 128
ReLU-7 [-1, 64, 56, 56] 0
Conv2d-8 [-1, 64, 56, 56] 36,864
BatchNorm2d-9 [-1, 64, 56, 56] 128
ReLU-10 [-1, 64, 56, 56] 0
BasicBlock-11 [-1, 64, 56, 56] 0
Conv2d-12 [-1, 64, 56, 56] 36,864
BatchNorm2d-13 [-1, 64, 56, 56] 128
ReLU-14 [-1, 64, 56, 56] 0
Conv2d-15 [-1, 64, 56, 56] 36,864
BatchNorm2d-16 [-1, 64, 56, 56] 128
ReLU-17 [-1, 64, 56, 56] 0
BasicBlock-18 [-1, 64, 56, 56] 0
Conv2d-19 [-1, 128, 28, 28] 73,728
BatchNorm2d-20 [-1, 128, 28, 28] 256
ReLU-21 [-1, 128, 28, 28] 0
Conv2d-22 [-1, 128, 28, 28] 147,456
BatchNorm2d-23 [-1, 128, 28, 28] 256
Conv2d-24 [-1, 128, 28, 28] 8,192
BatchNorm2d-25 [-1, 128, 28, 28] 256
ReLU-26 [-1, 128, 28, 28] 0
BasicBlock-27 [-1, 128, 28, 28] 0
Conv2d-28 [-1, 128, 28, 28] 147,456
BatchNorm2d-29 [-1, 128, 28, 28] 256
ReLU-30 [-1, 128, 28, 28] 0
Conv2d-31 [-1, 128, 28, 28] 147,456
BatchNorm2d-32 [-1, 128, 28, 28] 256
ReLU-33 [-1, 128, 28, 28] 0
BasicBlock-34 [-1, 128, 28, 28] 0
Conv2d-35 [-1, 256, 14, 14] 294,912
BatchNorm2d-36 [-1, 256, 14, 14] 512
ReLU-37 [-1, 256, 14, 14] 0
Conv2d-38 [-1, 256, 14, 14] 589,824
BatchNorm2d-39 [-1, 256, 14, 14] 512
Conv2d-40 [-1, 256, 14, 14] 32,768
BatchNorm2d-41 [-1, 256, 14, 14] 512
ReLU-42 [-1, 256, 14, 14] 0
BasicBlock-43 [-1, 256, 14, 14] 0
Conv2d-44 [-1, 256, 14, 14] 589,824
BatchNorm2d-45 [-1, 256, 14, 14] 512
ReLU-46 [-1, 256, 14, 14] 0
Conv2d-47 [-1, 256, 14, 14] 589,824
BatchNorm2d-48 [-1, 256, 14, 14] 512
ReLU-49 [-1, 256, 14, 14] 0
BasicBlock-50 [-1, 256, 14, 14] 0
Conv2d-51 [-1, 512, 7, 7] 1,179,648
BatchNorm2d-52 [-1, 512, 7, 7] 1,024
ReLU-53 [-1, 512, 7, 7] 0
Conv2d-54 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-55 [-1, 512, 7, 7] 1,024
Conv2d-56 [-1, 512, 7, 7] 131,072
BatchNorm2d-57 [-1, 512, 7, 7] 1,024
ReLU-58 [-1, 512, 7, 7] 0
BasicBlock-59 [-1, 512, 7, 7] 0
Conv2d-60 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-61 [-1, 512, 7, 7] 1,024
ReLU-62 [-1, 512, 7, 7] 0
Conv2d-63 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-64 [-1, 512, 7, 7] 1,024
ReLU-65 [-1, 512, 7, 7] 0
BasicBlock-66 [-1, 512, 7, 7] 0
AdaptiveAvgPool2d-67 [-1, 512, 1, 1] 0
Linear-68 [-1, 1000] 513,000
================================================================
Total params: 11,689,512
Trainable params: 11,689,512
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 62.79
Params size (MB): 44.59
Estimated Total Size (MB): 107.96
----------------------------------------------------------------
'''
通过torchsummary.summary可清晰地查看神经网络层次结构、每一层的输入数据和输出数据的形状（Shape）、模型的参数量（Params）等信息，方便可视化地了解模型结构、分析数据计算和传递过程。从以上结果可以看出，resnet18模型包含17个Conv2D卷积层、17个ReLU激活层、1个MaxPool2D池化层以及1个Linear全连接层，这些层通过堆叠形成了resnet18模型。
二. 使用torch.nn.Sequential组网
torch.nn.Sequential是PyTorch中的一个模型容器，用于将多个网络层按照顺序组合成一个网络模型。它的原理就是将各个网络层按照顺序连接起来，输出层的输出作为下一层的输入，最终得到整个网络的输出。
下面是一个使用torch.nn.Sequential构建resnet18模型的示例代码：
import torch
import torch.nn as nn
from torchsummary import summary
# 定义一个Sequential模型
model = nn.Sequential(
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Conv2d(256, 512, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Flatten(),
nn.Linear(512 * 3 * 3, 10),
nn.Softmax(dim=1)
)
# 定义一个输入张量，大小为(1, 64, 28, 28)
input_tensor = torch.randn(1, 64, 28, 28)
# 使用Sequential模型进行前向计算
output = model(input_tensor)
# 打印输出张量的大小
print(output.size())
# 打印模型结构和参数数量等信息
summary(model, (64, 28, 28))
'''
torch.Size([1, 10])
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 128, 28, 28] 73,856
BatchNorm2d-2 [-1, 128, 28, 28] 256
ReLU-3 [-1, 128, 28, 28] 0
MaxPool2d-4 [-1, 128, 14, 14] 0
Conv2d-5 [-1, 256, 14, 14] 295,168
BatchNorm2d-6 [-1, 256, 14, 14] 512
ReLU-7 [-1, 256, 14, 14] 0
MaxPool2d-8 [-1, 256, 7, 7] 0
Conv2d-9 [-1, 512, 7, 7] 1,180,160
BatchNorm2d-10 [-1, 512, 7, 7] 1,024
ReLU-11 [-1, 512, 7, 7] 0
MaxPool2d-12 [-1, 512, 3, 3] 0
Flatten-13 [-1, 4608] 0
Linear-14 [-1, 10] 46,090
Softmax-15 [-1, 10] 0
================================================================
Total params: 1,597,066
Trainable params: 1,597,066
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.19
Forward/backward pass size (MB): 4.38
Params size (MB): 6.09
Estimated Total Size (MB): 10.66
----------------------------------------------------------------
'''
三. 使用torch.nn.Module组网
torch.nn.Module是PyTorch中所有神经网络模块的基类，用于构建神经网络模型。它提供了一些常用的方法和属性，如forward()方法用于前向传播，parameters()方法用于获取模型的可训练参数等。
下面是一个使用torch.nn.Module构建resnet18模型的示例代码：
import torch
import torch.nn as nn
from torchsummary import summary
# 定义一个ResNet18模型
class ResNet18(nn.Module):
def __init__(self, num_classes=1000):
super(ResNet18, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU()
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = nn.Sequential(
ResidualBlock(64, 64),
ResidualBlock(64, 64)
)
self.layer2 = nn.Sequential(
ResidualBlock(64, 128, stride=2),
ResidualBlock(128, 128)
)
self.layer3 = nn.Sequential(
ResidualBlock(128, 256, stride=2),
ResidualBlock(256, 256)
)
self.layer4 = nn.Sequential(
ResidualBlock(256, 512, stride=2),
ResidualBlock(512, 512)
)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.flatten = nn.Flatten()
self.fc = nn.Linear(512, num_classes)
self.softmax = nn.Softmax(dim=1)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = self.flatten(x)
x = self.fc(x)
x = self.softmax(x)
return x
# 定义一个残差块
class ResidualBlock(nn.Module):
def __init__(self, in_channels, out_channels, stride=1):
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channels)
self.relu = nn.ReLU()
self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(out_channels)
self.downsample = None
if stride != 1 or in_channels != out_channels:
self.downsample = nn.Sequential(nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(out_channels))
def forward(self, x):
identity = x
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.conv2(x)
x = self.bn2(x)
if self.downsample is not None:
identity = self.downsample(identity)
x += identity
x = self.relu(x)
return x
# 创建一个ResNet18实例
model = ResNet18()
input_size = (3, 224, 224)
# 可视化模型组网结构和参数
params_info = summary(model, input_size)
print(params_info)
'''
----------------------------------------------------------------
Layer (type) Output Shape Param #
================================================================
Conv2d-1 [-1, 64, 112, 112] 9,472
BatchNorm2d-2 [-1, 64, 112, 112] 128
ReLU-3 [-1, 64, 112, 112] 0
MaxPool2d-4 [-1, 64, 56, 56] 0
Conv2d-5 [-1, 64, 56, 56] 36,864
BatchNorm2d-6 [-1, 64, 56, 56] 128
ReLU-7 [-1, 64, 56, 56] 0
Conv2d-8 [-1, 64, 56, 56] 36,864
BatchNorm2d-9 [-1, 64, 56, 56] 128
ReLU-10 [-1, 64, 56, 56] 0
ResidualBlock-11 [-1, 64, 56, 56] 0
Conv2d-12 [-1, 64, 56, 56] 36,864
BatchNorm2d-13 [-1, 64, 56, 56] 128
ReLU-14 [-1, 64, 56, 56] 0
Conv2d-15 [-1, 64, 56, 56] 36,864
BatchNorm2d-16 [-1, 64, 56, 56] 128
ReLU-17 [-1, 64, 56, 56] 0
ResidualBlock-18 [-1, 64, 56, 56] 0
Conv2d-19 [-1, 128, 28, 28] 73,728
BatchNorm2d-20 [-1, 128, 28, 28] 256
ReLU-21 [-1, 128, 28, 28] 0
Conv2d-22 [-1, 128, 28, 28] 147,456
BatchNorm2d-23 [-1, 128, 28, 28] 256
Conv2d-24 [-1, 128, 28, 28] 8,192
BatchNorm2d-25 [-1, 128, 28, 28] 256
ReLU-26 [-1, 128, 28, 28] 0
ResidualBlock-27 [-1, 128, 28, 28] 0
Conv2d-28 [-1, 128, 28, 28] 147,456
BatchNorm2d-29 [-1, 128, 28, 28] 256
ReLU-30 [-1, 128, 28, 28] 0
Conv2d-31 [-1, 128, 28, 28] 147,456
BatchNorm2d-32 [-1, 128, 28, 28] 256
ReLU-33 [-1, 128, 28, 28] 0
ResidualBlock-34 [-1, 128, 28, 28] 0
Conv2d-35 [-1, 256, 14, 14] 294,912
BatchNorm2d-36 [-1, 256, 14, 14] 512
ReLU-37 [-1, 256, 14, 14] 0
Conv2d-38 [-1, 256, 14, 14] 589,824
BatchNorm2d-39 [-1, 256, 14, 14] 512
Conv2d-40 [-1, 256, 14, 14] 32,768
BatchNorm2d-41 [-1, 256, 14, 14] 512
ReLU-42 [-1, 256, 14, 14] 0
ResidualBlock-43 [-1, 256, 14, 14] 0
Conv2d-44 [-1, 256, 14, 14] 589,824
BatchNorm2d-45 [-1, 256, 14, 14] 512
ReLU-46 [-1, 256, 14, 14] 0
Conv2d-47 [-1, 256, 14, 14] 589,824
BatchNorm2d-48 [-1, 256, 14, 14] 512
ReLU-49 [-1, 256, 14, 14] 0
ResidualBlock-50 [-1, 256, 14, 14] 0
Conv2d-51 [-1, 512, 7, 7] 1,179,648
BatchNorm2d-52 [-1, 512, 7, 7] 1,024
ReLU-53 [-1, 512, 7, 7] 0
Conv2d-54 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-55 [-1, 512, 7, 7] 1,024
Conv2d-56 [-1, 512, 7, 7] 131,072
BatchNorm2d-57 [-1, 512, 7, 7] 1,024
ReLU-58 [-1, 512, 7, 7] 0
ResidualBlock-59 [-1, 512, 7, 7] 0
Conv2d-60 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-61 [-1, 512, 7, 7] 1,024
ReLU-62 [-1, 512, 7, 7] 0
Conv2d-63 [-1, 512, 7, 7] 2,359,296
BatchNorm2d-64 [-1, 512, 7, 7] 1,024
ReLU-65 [-1, 512, 7, 7] 0
ResidualBlock-66 [-1, 512, 7, 7] 0
AdaptiveAvgPool2d-67 [-1, 512, 1, 1] 0
Flatten-68 [-1, 512] 0
Linear-69 [-1, 1000] 513,000
Softmax-70 [-1, 1000] 0
================================================================
Total params: 11,689,576
Trainable params: 11,689,576
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 62.80
Params size (MB): 44.59
Estimated Total Size (MB): 107.97
----------------------------------------------------------------
'''