● 语言环境:Python3.8
● 编译器:pycharm
● 深度学习环境:Pytorch
● 数据来源:链接:https://pan.baidu.com/s/1gA3TXAWpil9l39wJMjwuRA 提取码:zj37
# -*- coding: utf-8 -*-
import torch.utils.data
from torchvision import datasets, transforms
from model import *
# 一、加载数据并处理
train_data_path = './data/train/'
test_data_path = './data/test/'
# 加载文件夹中的数据
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor,并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布(高斯分布),使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
test_transforms = transforms.Compose([
transforms.Resize([224, 224]),
transforms.ToTensor(),
transforms.Normalize( # 标准化处理-->转换为标准正太分布(高斯分布),使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
train_dataset = datasets.ImageFolder(train_data_path, transform=train_transforms)
test_dataset = datasets.ImageFolder(test_data_path, transform=test_transforms)
# 将数据进行批次处理
batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_dl = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size)
# 二、构建模型网络 model.__init__, model.forward()
# 三、模型训练
# 实例化模型
device = 'cuda' if torch.cuda.is_available() else 'cpu'
print('Using {} device:'.format(device))
model = Network_fn().to(device)
# 设置参数
def adjust_learning_rate(optimizer, epoch, start_lr):
# 每两个epoch学习率删减到原来的0.92
lr = start_lr * (0.92 ** (epoch // 2))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
learn_rate = 1e-4 # 初始学习率
optimizer = torch.optim.SGD(model.parameters(), lr=learn_rate)
loss_fn = nn.CrossEntropyLoss()
# 模型训练
epochs = 50
train_loss = []
train_acc = []
test_loss = []
test_acc = []
for epoch in range(epochs):
# 更新学习率
adjust_learning_rate(optimizer, epoch, learn_rate)
model.train()
epoch_train_acc, epoch_train_loss = model.train1(train_dl, model, loss_fn, optimizer, device)
model.eval()
epoch_test_acc, epoch_test_loss = model.test1(test_dl, model, loss_fn, device)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
# 获取当前的学习率
lr = optimizer.state_dict()['param_groups'][0]['lr']
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')
print(template.format(epoch + 1, epoch_train_acc * 100, epoch_train_loss,
epoch_test_acc * 100, epoch_test_loss, lr))
print('Done')
# 保存模型
torch.save(model.state_dict(), './model/model.pkl')
# 四、模型评估
import matplotlib.pyplot as plt
# 隐藏警告
import warnings
epochs_range = range(epochs)
warnings.filterwarnings("ignore") # 忽略警告信息
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
plt.rcParams['figure.dpi'] = 100 # 分辨率
plt.figure(figsize=(20, 5))
plt.subplot(1, 2, 1)
plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')
plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()
# -*- coding: utf-8 -*-
import torch
import torch.nn as nn
class Network_fn(nn.Module):
def __init__(self):
super(Network_fn, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(3, 12, kernel_size=5, padding=0),
nn.BatchNorm2d(12),
nn.ReLU()
)
self.conv2 = nn.Sequential(
nn.Conv2d(12, 12, kernel_size=5, padding=0),
nn.BatchNorm2d(12),
nn.ReLU()
)
self.pool3 = nn.Sequential(
nn.MaxPool2d(2)
)
self.conv4 = nn.Sequential(
nn.Conv2d(12, 24, kernel_size=5, padding=0),
nn.BatchNorm2d(24),
nn.ReLU()
)
self.conv5 = nn.Sequential(
nn.Conv2d(24, 24, kernel_size=5, padding=0),
nn.BatchNorm2d(24),
nn.ReLU()
)
self.pool6 = nn.Sequential(
nn.MaxPool2d(2)
)
self.dropout = nn.Sequential(
nn.Dropout(0.2)
)
self.fc = nn.Sequential(
nn.Linear(24 * 50 * 50, 2)
)
def forward(self, x):
batch_size = x.size(0)
x = self.conv1(x)
x = self.conv2(x)
x = self.pool3(x)
x = self.conv4(x)
x = self.conv5(x)
x = self.pool6(x)
x = self.dropout(x)
x = x.view(batch_size, -1) # flatten 变成全连接网络需要的输入 (batch, 24*50*50) ==> (batch, -1), -1 此处自动算出的是24*50*50
x = self.fc(x)
return x
def train1(self, dataloader, model, loss_fn, optimizer, device):
train_acc, train_loss = 0, 0
for X, y in dataloader:
X, y = X.to(device), y.to(device)
# 前向传播
pred = model(X)
loss = loss_fn(pred, y)
# 反向传播
optimizer.zero_grad() # 梯度归零
loss.backward()
optimizer.step() # 更新参数
train_acc += (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss += train_loss
size = len(dataloader.dataset)
num_batches = len(dataloader)
train_acc /= size
train_loss /= num_batches
return train_acc, train_loss
def test1(self, dataloader, model, loss_fn, device):
size = len(dataloader.dataset) # 测试集的大小
num_batches = len(dataloader) # 批次数目, (size/batch_size,向上取整)
test_loss, test_acc = 0, 0
with torch.no_grad():
for imgs, target in dataloader:
imgs, target = imgs.to(device), target.to(device)
# 计算loss
target_pred = model(imgs)
loss = loss_fn(target_pred, target)
test_loss += loss.item()
test_acc += (target_pred.argmax(1) == target).type(torch.float).sum().item()
test_acc /= size
test_loss /= num_batches
return test_acc, test_loss
# -*- coding: utf-8 -*-
import torch
from PIL import Image
from matplotlib import pyplot as plt
from torchvision import transforms
from model import Network_fn
device = 'cuda' if torch.cuda.is_available() else 'cpu'
model = Network_fn()
model.load_state_dict(torch.load('./model/model.pkl', map_location=torch.device('cpu')))
path = './data/test/adidas/2.jpg'
test_img = Image.open(path).convert('RGB')
plt.imshow(test_img)
plt.show()
t_transforms = transforms.Compose([
transforms.Resize([224, 224]),
transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.ToTensor(),
])
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor,并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布(高斯分布),使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
test_img = train_transforms(test_img)
test_img = test_img.unsqueeze(0)
model.eval()
output = model(test_img)
index = output.argmax(1)
classes = ['adidas', 'nike']
print(classes[index])
test.py对单个照片进行预测的时候,怎么预测都不对,最后把transforms改成了之前的train_transform解决了。
我之前写的transforms是这样的,考虑到时测试,没必须要加太多的参数
t_transforms = transforms.Compose([
transforms.Resize([224, 224]),
transforms.ToTensor(),
])
最后改为:
train_transforms = transforms.Compose([
transforms.Resize([224, 224]), # 将输入图片resize成统一尺寸
# transforms.RandomHorizontalFlip(), # 随机水平翻转
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor,并归一化到[0,1]之间
transforms.Normalize( # 标准化处理-->转换为标准正太分布(高斯分布),使模型更容易收敛
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]) # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])
搞定