CNN运动鞋识别
数据集https://www.heywhale.com/mw/dataset/62feeea455804632ba14168d/file
上次的代码改一下dataloader，84%正确率直接过
```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 = './spot_photos/train'
data_dir = pathlib.Path(data_dir)
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=)
])
train_dataset = datasets.ImageFolder("./spot_photos/train/",transform=train_transforms)
test_dataset= datasets.ImageFolder("./spot_photos/test/",transform=train_transforms)
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__()
self.conv1 = nn.Conv2d(3, 12, 5, stride=1, padding=2)
self.bn1 = nn.BatchNorm2d(12)
self.conv2 = nn.Conv2d(12, 12, 5, stride=1, padding=2)
self.bn2 = nn.BatchNorm2d(12)
self.pool = nn.MaxPool2d(2,2)
self.conv4 = nn.Conv2d(12, 24, 5, stride=1, padding=2)
self.bn4 = nn.BatchNorm2d(24)
self.conv5 = nn.Conv2d(24, 24, 5, stride=1, padding=2)
self.bn5 = nn.BatchNorm2d(24)
# 添加dropout
self.dropout = nn.Dropout(0.2)
self.fc1 = nn.Linear(24*56*56, len(classeNames))
def forward(self, x):
x = F.relu(self.bn1(self.conv1(x)))
x = F.relu(self.bn2(self.conv2(x)))
x = self.pool(x)
x = F.relu(self.bn4(self.conv4(x)))
x = F.relu(self.bn5(self.conv5(x)))
x = self.pool(x)
x = x.view(-1, 24*56*56)
x = self.dropout(x)# 在全连接前加dropout
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-3 # 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))
torch.save(model.state_dict(), f'best_model_epoch{epoch}.pth')
print('Done')
checkpoint_path = 'best_model_epoch19.pth'
if os.path.exists(checkpoint_path):
state_dict = torch.load(checkpoint_path, map_location=device)
model.load_state_dict(state_dict)
start_epoch = 20
else:
start_epoch = 0
loss_fn = nn.CrossEntropyLoss()
new_lr = 1e-4
opt = torch.optim.SGD(model.parameters(), lr=new_lr, momentum=0.9, weight_decay=1e-4)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(opt, mode='min', factor=0.5, patience=3)
extra_epochs = 10
train_loss = []
train_acc= []
test_loss= []
test_acc = []
for epoch in range(start_epoch, start_epoch + extra_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)
# 调度器基于验证损失调整学习率
scheduler.step(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))
torch.save(model.state_dict(), f'best_model_epoch_END.pth')
print('Done')
```
页:
[1]