CNN天气识别
数据集https://www.heywhale.com/mw/dataset/60d9bd7c056f570017c305ee/file
主要区别就是dataloader部分
其他代码基本一致
```python
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import torch.nn.functional as F
import os,PIL,pathlib
import os,PIL,random,pathlib
data_dir = './weather_photos/'
data_dir = pathlib.Path(data_dir)
total_datadir = './weather_photos/'
data_paths = list(data_dir.glob('*'))
classeNames = for path in data_paths]
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
train_transforms = transforms.Compose([
transforms.Resize(),# 将输入图片resize成统一尺寸
transforms.ToTensor(), # 将PIL Image或numpy.ndarray转换为tensor，并归一化到之间
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=,
std=)# 其中 mean=与std= 从数据集中随机抽样计算得到的。
])
total_data = datasets.ImageFolder(total_datadir,transform=train_transforms)
train_size = int(0.8 * len(total_data))
test_size= len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, )
print(f"训练集样本数: {len(train_dataset)}")
print(f"测试集样本数: {len(test_dataset)}")
batch_size = 32
def make_dataloaders(train_dataset, test_dataset, batch_size=32, num_workers=0):
train_dl = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=num_workers)
test_dl = torch.utils.data.DataLoader(test_dataset,
batch_size=batch_size,
shuffle=True,
num_workers=num_workers)
return train_dl, test_dl
class Network_bn(nn.Module):
def __init__(self):
super(Network_bn, self).__init__()
"""
保持原始结构，只做最小必要的改进
"""
# 关键改进：添加padding保持特征图尺寸
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=2)# 224→224
self.bn1 = nn.BatchNorm2d(12)
self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=2)# 224→224
self.bn2 = nn.BatchNorm2d(12)
self.pool = nn.MaxPool2d(2,2)# 224→112
self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=2)# 112→112
self.bn4 = nn.BatchNorm2d(24)
self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=2)# 112→112
self.bn5 = nn.BatchNorm2d(24)
# pool: 112→56
# 保持原始的全连接层设计
self.fc1 = nn.Linear(24*56*56, len(classeNames))
def forward(self, x):
x = F.relu(self.bn1(self.conv1(x))) # 224→224
x = F.relu(self.bn2(self.conv2(x))) # 224→224
x = self.pool(x) # 224→112
x = F.relu(self.bn4(self.conv4(x))) # 112→112
x = F.relu(self.bn5(self.conv5(x))) # 112→112
x = self.pool(x) # 112→56
x = x.view(-1, 24*56*56) # 展平
x = self.fc1(x)
return x
model = Network_bn().to(device)
def test (dataloader, model, loss_fn):
size = len(dataloader.dataset)# 测试集的大小，一共10000张图片
num_batches = len(dataloader) # 批次数目，313（10000/32=312.5，向上取整）
test_loss, test_acc = 0, 0
# 当不进行训练时，停止梯度更新，节省计算内存消耗
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
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset)# 训练集的大小，一共60000张图片
num_batches = len(dataloader) # 批次数目，1875（60000/32）
train_loss, train_acc = 0, 0# 初始化训练损失和正确率
for X, y in dataloader:# 获取图片及其标签
X, y = X.to(device), y.to(device)
# 计算预测误差
pred = model(X) # 网络输出
loss = loss_fn(pred, y)# 计算网络输出和真实值之间的差距，targets为真实值，计算二者差值即为损失
# 反向传播
optimizer.zero_grad()# grad属性归零
loss.backward() # 反向传播
optimizer.step() # 每一步自动更新
# 记录acc与loss
train_acc+= (pred.argmax(1) == y).type(torch.float).sum().item()
train_loss += loss.item()
train_acc/= size
train_loss /= num_batches
return train_acc, train_loss
# On Windows the DataLoader with multiple workers requires the
# `if __name__ == '__main__'` guard. Use next(iter(...)) to fetch
# a single batch without indexing the DataLoader.
train_dl, test_dl = make_dataloaders(train_dataset, test_dataset, batch_size=batch_size, num_workers=0)
batch = next(iter(test_dl))
X, y = batch
print("Shape of X : ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
loss_fn = nn.CrossEntropyLoss() # 创建损失函数
learn_rate = 1e-4 # 学习率
opt = torch.optim.SGD(model.parameters(),lr=learn_rate)
epochs = 20
train_loss = []
train_acc= []
test_loss= []
test_acc = []
for epoch in range(epochs):
model.train()
epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, opt)
model.eval()
epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)
train_acc.append(epoch_train_acc)
train_loss.append(epoch_train_loss)
test_acc.append(epoch_test_acc)
test_loss.append(epoch_test_loss)
template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%，Test_loss:{:.3f}')
print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss))
print('Done')
```
页:
[1]