kaggle猫狗识别pytorch

https://zhuanlan.zhihu.com/p/136421422

数据集下载

链接：https://pan.baidu.com/s/1KZlADFFgI1zd_ia10U5FWw 
提取码：r7wn 
复制这段内容后打开百度网盘手机App，操作更方便哦

dataset.py(注意处理标签的技巧)

# -*- encoding: utf-8 -*-
"""
@File    : dataset.py
@Time    : 2021-04-20 17:17
@Author  : XD
@Email   : gudianpai@qq.com
@Software: PyCharm
"""
import os
from PIL import Image
import torch
from torch.utils import data
import numpy as np
from torchvision import transforms
from torch.utils.data import DataLoader

class DogCat(data.Dataset):
    def __init__(self, root, transforms = None):
        imgs = os.listdir(root)
        # 所有图片的绝对路径
        # 不加载照片只指定路径
        # 当调用_getitem_时才会真正读图片
        self.imgs = [os.path.join(root, img) for img in imgs]
        self.transforms = transforms

    def __getitem__(self, index):
        img_path = self.imgs[index]
        #dog ->0 cat ->1
        label = 1 if 'dog' in img_path.split('/')[-1] else 0
        data = Image.open(img_path)
        if self.transforms:
            data = self.transforms(data)
        return data,label

    def __len__(self):
        return len(self.imgs)
transform = transforms.Compose([
    transforms.Resize([224,224]),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
]
)

train_dataset = DogCat("./catdog/train",transforms = transform)
train_loader = DataLoader(train_dataset,shuffle = True,batch_size = 32)

test_dataset = DogCat("./catdog/test",transforms = transform)
test_loader = DataLoader(test_dataset,shuffle = False,batch_size = 32)

if __name__ == '__main__':
    dataset = DogCat("./catdog/test",transforms = transform)
    for img, label in dataset:
        print(img.size(),label)

net.py

# -*- encoding: utf-8 -*-
"""
@File    : net.py
@Time    : 2021-04-20 17:12
@Author  : XD
@Email   : gudianpai@qq.com
@Software: PyCharm
"""
import torch
from torchvision import models

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
import torch.nn as nn

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.maxpool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 53 * 53, 1024)
        self.fc2 = nn.Linear(1024, 512)
        self.fc3 = nn.Linear(512, 2)

    def forward(self, x):
        x = self.maxpool(F.relu(self.conv1(x)))
        x = self.maxpool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 53 * 53)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)

        return x

if __name__ == '__main__':
    net = Net()
    print(net)

主函数main.py

# -*- encoding: utf-8 -*-
"""
@File    : main.py
@Time    : 2021-04-20 17:16
@Author  : XD
@Email   : gudianpai@qq.com
@Software: PyCharm
"""
import torch
import torch.optim as optim
from ResNet50 import ResNet50
from dataset import test_loader
from dataset import train_loader

model = ResNet50()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9,weight_decay = 0.01)

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()
        # forward + backward + update
        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if batch_idx % 10 == 9:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 10))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            #print("实际上的label:",labels)
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            #print("model预测的label:", predicted)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
        print('Accuracy on test set: %d %%' % (100 * correct / total))
if __name__ == '__main__':
    for epoch in range(20):
        train(epoch)
        test()

准确率好像一般。。。。。我训练了一轮然后结果是57%,需要进一步的改进。