第五课简单图片分类

可爱的小山楂

已于 2022-08-30 08:59:03 修改

阅读量202

点赞数

分类专栏： pytorch学习笔记文章标签： python

于 2021-07-05 19:55:02 首次发布

本文链接：https://blog.csdn.net/qq_44177462/article/details/118496976

版权

本篇博客探讨了如何使用预训练的卷积神经网络（CNN）模型进行迁移学习，以加速图像分类任务的训练。介绍了LeNet、AlexNet、VGG-16、ResNet和DenseNet等常见CNN架构，并展示了在PyTorch中进行迁移学习的基本步骤，包括数据预处理、模型初始化、调整输出层、选择优化器以及模型训练。实例中使用了hymenoptera_data数据集，包含bees和ants两类图片。

摘要由CSDN通过智能技术生成

》常见的ConvNet架构

INPUT -> [[CONV -> RELU] * N -> POOL] * M -> [FC -> RELU]*K -> FC

》LeNet Yann Lecun, 1998年

》AlexNet

》VGG-16

》ResNet，学习每层的改变

》DenseNet

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
print("PyTorch Version: ",torch.__version__)

PyTorch Version:  1.0.0

首先我们定义一个基于ConvNet的简单神经网络

In [4]:

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5, 1)
        self.conv2 = nn.Conv2d(20, 50, 5, 1)
        self.fc1 = nn.Linear(4*4*50, 500)
        self.fc2 = nn.Linear(500, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2, 2)
        x = x.view(-1, 4*4*50)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

NLL loss的定义

ℓ(x,y)=L={l1,…,lN}⊤,ln=−wynxn,yn,wc=weight[c]⋅1{c≠ignore\_index}ℓ(x,y)=L={l1,…,lN}⊤,ln=−wynxn,yn,wc=weight[c]⋅1{c≠ignore\_index}

In [7]:

def train(model, device, train_loader, optimizer, epoch, log_interval=100):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % log_interval == 0:
            print("Train Epoch: {} [{}/{} ({:0f}%)]\tLoss: {:.6f}".format(
                epoch, batch_idx * len(data), len(train_loader.dataset), 
                100. * batch_idx / len(train_loader), loss.item()
            ))

In [8]:

def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True) # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))

In [13]:

torch.manual_seed(53113)

use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
batch_size = test_batch_size = 32
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('./mnist_data', train=True, download=True,
                   transform=transforms.Compose([
                       t