Note that the final result of convolution is still a feature map, which needs to be converted into a vector to do classification or regression tasksclass CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Sequential( # 输入大小 (1, 28, 28)
nn.Conv2d(
in_channels=1, # 灰度图
out_channels=16, # 要得到几多少个特征图
kernel_size=5, # 卷积核大小
stride=1, # 步长
padding=2, # 如果希望卷积后大小跟原来一样,需要设置padding=(kernel_size-1)/2 if stride=1
), # 输出的特征图为 (16, 28, 28)
nn.ReLU(), # relu层
nn.MaxPool2d(kernel_size=2), # 进行池化操作(2x2 区域), 输出结果为: (16, 14, 14)
)
self.conv2 = nn.Sequential( # 下一个套餐的输入 (16, 14, 14)
nn.Conv2d(16, 32, 5, 1, 2), # 输出 (32, 14, 14)
nn.ReLU(), # relu层
nn.Conv2d(32, 32, 5, 1, 2),
nn.ReLU(),
nn.MaxPool2d(2), # 输出 (32, 7, 7)
)
self.conv3 = nn.Sequential( # 下一个套餐的输入 (16, 14, 14)
nn.Conv2d(32, 64, 5, 1, 2), # 输出 (32, 14, 14)
nn.ReLU(), # 输出 (32, 7, 7)
)
self.out = nn.Linear(64 * 7 * 7, 10) # 全连接层得到的结果
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = self.conv3(x)
x = x.view(x.size(0), -1) # flatten操作,结果为:(batch_size, 32 * 7 * 7)
output = self.out(x)
return output
Accuracy as an evaluation criterion
def accuracy(predictions, labels):
pred = torch.max(predictions.data, 1)[1]
rights = pred.eq(labels.data.view_as(pred)).sum()
return rights, len(labels)
Train the network model
# 实例化
net = CNN()
#损失函数
criterion = nn.CrossEntropyLoss()
#优化器
optimizer = optim.Adam(net.parameters(), lr=0.001) #定义优化器,普通的随机梯度下降算法
#开始训练循环
for epoch in range(num_epochs):
#当前epoch的结果保存下来
train_rights = []
for batch_idx, (data, target) in enumerate(train_loader): #针对容器中的每一个批进行循环
net.train()
output = net(data)
loss = criterion(output, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
right = accuracy(output, target)
train_rights.append(right)
if batch_idx % 100 == 0:
net.eval()
val_rights = []
for (data, target) in test_loader:
output = net(data)
right = accuracy(output, target)
val_rights.append(right)
#准确率计算
train_r = (sum([tup[0] for tup in train_rights]), sum([tup[1] for tup in train_rights]))
val_r = (sum([tup[0] for tup in val_rights]), sum([tup[1] for tup in val_rights]))
print('当前epoch: {} [{}/{} ({:.0f}%)]\t损失: {:.6f}\t训练集准确率: {:.2f}%\t测试集正确率: {:.2f}%'.format(
epoch, batch_idx * batch_size, len(train_loader.dataset),
100. * batch_idx / len(train_loader),
loss.data,
100. * train_r[0].numpy() / train_r[1],
100. * val_r[0].numpy() / val_r[1]))
Current epoch: 0 [0/60000 (0%)] Loss: 2.300918 Training set accuracy: 10.94% Test set accuracy: 10.10%
Current epoch: 0 [6400/60000 (11%)] Loss: 0.204191 Training set accuracy: 78.06% Test set accuracy: 93.31%
Current epoch: 0 [12800/60000 (21%)] Loss: 0.039503 Training set accuracy: 86.51% Test set accuracy: 96.69%
Current epoch: 0 [19200/60000 (32%)] Loss: 0.057866 Training set accuracy: 89.93% Test set accuracy: 97.54%
Current epoch: 0 [25600/60000 (43%)] Loss: 0.069566 Training set accuracy: 91.68% Test set accuracy: 97.68%
Current epoch: 0 [32000/60000 (53%)] Loss: 0.228793 Training set accuracy: 92.85% Test set accuracy: 98.18%
Current epoch: 0 [38400/60000 (64%)] Loss: 0.111003 Training set accuracy: 93.72% Test set accuracy: 98.16%
Current epoch: 0 [44800/60000 (75%)] Loss: 0.110226 Training set accuracy: 94.28% Test set accuracy: 98.44%
Current epoch: 0 [51200/60000 (85%)] Loss: 0.014538 Training set accuracy: 94.78% Test set accuracy: 98.60%
Current epoch: 0 [57600/60000 (96%)] Loss: 0.051019 Training set accuracy: 95.14% Test set accuracy: 98.45%
Current epoch: 1 [0/60000 (0%)] Loss: 0.036383 Training set accuracy: 98.44% Test set accuracy: 98.68%
Current epoch: 1 [6400/60000 (11%)] Loss: 0.088116 Training set accuracy: 98.50% Test set accuracy: 98.37%
Current epoch: 1 [12800/60000 (21%)] Loss: 0.120306 Training set accuracy: 98.59% Test set accuracy: 98.97%
Current epoch: 1 [19200/60000 (32%)] Loss: 0.030676 Training set accuracy: 98.63% Test set accuracy: 98.83%
Current epoch: 1 [25600/60000 (43%)] Loss: 0.068475 Training set accuracy: 98.59% Test set accuracy: 98.87%
Current epoch: 1 [32000/60000 (53%)] Loss: 0.033244 Training set accuracy: 98.62% Test set accuracy: 99.03%
Current epoch: 1 [38400/60000 (64%)] Loss: 0.024162 Training set accuracy: 98.67% Test set accuracy: 98.81%
Current epoch: 1 [44800/60000 (75%)] Loss: 0.006713 Training set accuracy: 98.69% Test set accuracy: 98.17%
Current epoch: 1 [51200/60000 (85%)] Loss: 0.009284 Training set accuracy: 98.69% Test set accuracy: 98.97%
Current epoch: 1 [57600/60000 (96%)] Loss: 0.036536 Training set accuracy: 98.68% Test set accuracy: 98.97%
Current epoch: 2 [0/60000 (0%)] Loss: 0.125235 Training set accuracy: 98.44% Test set accuracy: 98.73%
Current epoch: 2 [6400/60000 (11%)] Loss: 0.028075 Training set accuracy: 99.13% Test set accuracy: 99.17%
Current epoch: 2 [12800/60000 (21%)] Loss: 0.029663 Training set accuracy: 99.26% Test set accuracy: 98.39%
Current epoch: 2 [19200/60000 (32%)] Loss: 0.073855 Training set accuracy: 99.20% Test set accuracy: 98.81%
Current epoch: 2 [25600/60000 (43%)] Loss: 0.018130 Training set accuracy: 99.16% Test set accuracy: 99.09%
Current epoch: 2 [32000/60000 (53%)] Loss: 0.006968 Training set accuracy: 99.15% Test set accuracy: 99.11%