目录
引言
在深度学习和计算机视觉的世界里，MNIST数据集就像一颗璀璨的明珠，被广大研究者们珍视并广泛使用。这个数据集包含了大量的手写数字图像，为图像分类任务提供了丰富的素材。今天，我们将带您一同探索如何利用轻量级的深度神经网络MobileNet V2来处理MNIST数据集的图像分类任务。
MobileNet V2，正如其名，是MobileNet的第二代版本，它继承了MobileNet的轻量级和高效性能，同时进一步优化了结构和训练方法，使其在图像分类任务中表现得更为出色。
我们将通过详细的步骤，向您展示如何使用PyTorch实现这一任务。PyTorch是一个流行的深度学习框架，它提供了简洁易用的API和强大的计算能力，使得深度学习变得更加容易和高效。
在我们的示例代码中，我们将提供详细的注释，帮助您更好地理解每一步的操作和原理。我们希望通过这种方式，不仅让您学会如何使用MobileNet V2处理MNIST数据集的图像分类任务，更让您深入了解深度学习的原理和实现过程。
1. 安装PyTorch
# CUDA 11.6
pip install torch==1.12.1+cu116 torchvision==0.13.1+cu116 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu116
# CUDA 11.3
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113
# CUDA 10.2
pip install torch==1.12.1+cu102 torchvision==0.13.1+cu102 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu102
# CPU only
pip install torch==1.12.1+cpu torchvision==0.13.1+cpu torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cpu
2. 下载并加载MNIST数据集
import torch
import torchvision
import torchvision.transforms as transforms
# 数据预处理
transform = transforms.Compose(
[transforms.Resize((224, 224)), # 将图像resize成224×224
transforms.ToTensor(), # 将像素值缩放到0-1之间，并转换为Tensor
transforms.Normalize((0.5,), (0.5,))]) # 标准化
# 自动下载MNIST数据集并进行数据集【封装】
trainset = torchvision.datasets.MNIST(root='./data', train=True, transform=transform, download=True)
testset = torchvision.datasets.MNIST(root='./data', train=False, transform=transform, download=True)
# 设置训练集数据加载器和测试集数据加载器
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)
testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=False)
3. 搭建基于MobileNet V2的图像分类模型
import torch.nn as nn
# 加载预训练的MobilNet V2模型
model = mobilenet_v2(pretrained=True)
print("修改网络结构前:\n", model)
# 修改第一层，以满足MNIST数据集输入单通道的要求
model.features[0][0] = nn.Conv2d(1, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
# 修改最后一层，以满足MNIST数据集的10个类别的要求
model.classifier[-1] = nn.Linear(1280, 10)
print("修改网络结构后:\n", model)
运行结果（重点看网络开头和结束位置即可）
修改网络结构前:
MobileNetV2(
(features): Sequential(
(0): ConvBNReLU(
(0): Conv2d(3, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
(2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(2): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(3): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=144, bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(4): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(144, 144, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=144, bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(144, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(5): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(6): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(7): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(8): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(9): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(10): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(11): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(12): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(13): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(14): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(15): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(16): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(17): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(18): ConvBNReLU(
(0): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(classifier): Sequential(
(0): Dropout(p=0.2, inplace=False)
(1): Linear(in_features=1280, out_features=1000, bias=True)
)
)
修改网络结构后:
MobileNetV2(
(features): Sequential(
(0): ConvBNReLU(
(0): Conv2d(1, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=32, bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): Conv2d(32, 16, kernel_size=(1, 1), stride=(1, 1), bias=False)
(2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(2): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(16, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(96, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=96, bias=False)
(1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(96, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(3): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(144, 144, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=144, bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(144, 24, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(4): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(144, 144, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=144, bias=False)
(1): BatchNorm2d(144, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(144, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(5): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(6): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(7): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(192, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=192, bias=False)
(1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(192, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(8): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(9): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(10): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(11): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(64, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
(1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(12): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(13): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(14): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(96, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(576, 576, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=576, bias=False)
(1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(576, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(15): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(16): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(17): InvertedResidual(
(conv): Sequential(
(0): ConvBNReLU(
(0): Conv2d(160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(1): ConvBNReLU(
(0): Conv2d(960, 960, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=960, bias=False)
(1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
(2): Conv2d(960, 320, kernel_size=(1, 1), stride=(1, 1), bias=False)
(3): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(18): ConvBNReLU(
(0): Conv2d(320, 1280, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(1280, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU6(inplace=True)
)
)
(classifier): Sequential(
(0): Dropout(p=0.2, inplace=False)
(1): Linear(in_features=1280, out_features=10, bias=True)
)
)
4. 设置超参数、损失函数、优化器
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 判断是否使用GPU进行训练，如果有GPU则使用GPU进行训练，否则使用CPU。
criterion = nn.CrossEntropyLoss() # 定义损失函数
optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9) # 定义优化器
num_epochs = 20 # 定义训练轮数
running_loss = 0.0 # 累计损失函数值
model.to(device) # 将模型移动到指定设备上
5. 训练模型
# 开始模型训练循环
for epoch in range(num_epochs): # 遍历整个数据集多次
for i, (inputs, labels) in enumerate(trainloader): # 获取输入数据和标签
inputs, labels = inputs.to(device), labels.to(device) # 将数据移动到GPU上
optimizer.zero_grad() # 清空之前梯度缓存
outputs = model(inputs) # 前向传播，得到预测结果
loss = criterion(outputs, labels) # 计算损失函数值
loss.backward() # 反向传播，计算梯度值
optimizer.step() # 更新模型参数
running_loss += loss.item() # 累计损失函数值
if epoch % 10 == 0: # 每10个epoch打印一次训练信息
print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch + 1, num_epochs, running_loss / len(trainloader)))
6. 测试模型
correct = 0 # 定义准确率变量
total = 0 # 定义总样本数变量
# 开始模型测试循环
with torch.no_grad(): # 不需要计算梯度，也不需要更新模型参数
for inputs, labels in testloader: # 获取输入数据和标签
inputs, labels = inputs.to(device), labels.to(device) # 将数据移动到指定设备上
outputs = model(inputs) # 前向传播，得到预测结果
_, predicted = torch.max(outputs.data, 1) # 获取最大概率的类别作为预测结果
total += labels.size(0) # 增加总样本数
correct += (predicted == labels).sum().item() # 统计预测正确的样本数
print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
运行结果
完整代码
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
import torch
from torchvision import datasets, transforms
from torchvision.models import mobilenet_v2
import torch.nn as nn
# 数据预处理，将像素值缩放到0-1之间，转换为Tensor
transform = transforms.Compose(
[transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))])
# 加载训练数据集
trainset = datasets.MNIST('~/.pytorch/MNIST_data/', download=True, train=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)
# 加载测试数据集
testset = datasets.MNIST('~/.pytorch/MNIST_data/', download=True, train=False, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=True)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") # 判断是否使用GPU进行训练，如果有GPU则使用GPU进行训练，否则使用CPU。
# 加载预训练的MobilNet V2模型
model = mobilenet_v2(pretrained=True)
print("修改网络结构前:\n", model)
# 修改第一层，以满足MNIST数据集输入单通道的要
# 求
model.features[0][0] = nn.Conv2d(1, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
# 修改最后一层，以满足MNIST数据集的10个类别的要求
model.classifier[-1] = nn.Linear(1280, 10)
print("修改网络结构后:\n", model)
criterion = nn.CrossEntropyLoss() # 定义损失函数
optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9) # 定义优化器
num_epochs = 20 # 定义训练轮数
running_loss = 0.0 # 累计损失函数值
model.to(device) # 将模型移动到指定设备上
# 开始模型训练循环
for epoch in range(num_epochs): # 遍历整个数据集多次
for i, (inputs, labels) in enumerate(trainloader): # 获取输入数据和标签
inputs, labels = inputs.to(device), labels.to(device) # 将数据移动到GPU上
optimizer.zero_grad() # 清空之前梯度缓存
outputs = model(inputs) # 前向传播，得到预测结果
loss = criterion(outputs, labels) # 计算损失函数值
loss.backward() # 反向传播，计算梯度值
optimizer.step() # 更新模型参数
running_loss += loss.item() # 累计损失函数值
if epoch % 10 == 0: # 每10个epoch打印一次训练信息
print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch + 1, num_epochs, running_loss / len(trainloader)))
correct = 0 # 定义准确率变量
total = 0 # 定义总样本数变量
# 开始模型测试循环
with torch.no_grad(): # 不需要计算梯度，也不需要更新模型参数
for inputs, labels in testloader: # 获取输入数据和标签
inputs, labels = inputs.to(device), labels.to(device) # 将数据移动到指定设备上
outputs = model(inputs) # 前向传播，得到预测结果
_, predicted = torch.max(outputs.data, 1) # 获取最大概率的类别作为预测结果
total += labels.size(0) # 增加总样本数
correct += (predicted == labels).sum().item() # 统计预测正确的样本数
print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
结束语
- 亲爱的读者，感谢您花时间阅读我们的博客。我们非常重视您的反馈和意见，因此在这里鼓励您对我们的博客进行评论。
- 您的建议和看法对我们来说非常重要，这有助于我们更好地了解您的需求，并提供更高质量的内容和服务。
- 无论您是喜欢我们的博客还是对其有任何疑问或建议，我们都非常期待您的留言。让我们一起互动，共同进步！谢谢您的支持和参与！
- 我会坚持不懈地创作，并持续优化博文质量，为您提供更好的阅读体验。
- 谢谢您的阅读！