Pytorch之MNIST数据集实现
Pytorch之MNIST数据集实现
- 1. 全连接实现
- 2. CNN实现
提示：如果数据集下载失败，可以直接从网上下载四个数据集到raw文件夹下，dataset和项目为同级目录，例如：C:\Users\dell\PycharmProjects\dataset\mnist\MNIST\raw
1. 全连接实现
代码如下（示例）：
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
batch_size = 64
# transforms.ToTensor()：Covert the PIL Image to Tensor
# transforms.Normalize:The PARAMETERS are mean and std respectively,It use formulation x=(x-mean)/std
transform = transforms.Compose([transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])
train_dataset = datasets.MNIST(root='./dataset/mnist/',
train=True,
download=True,
transform=transform)
train_loader = DataLoader(train_dataset,
shuffle=True,
batch_size=batch_size)
test_dataset = datasets.MNIST(root='./dataset/mnist/',
train=False,
download=True,
transform=transform)
test_loader = DataLoader(test_dataset,
shuffle=False,
batch_size=batch_size)
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.l1 = torch.nn.Linear(784, 512)
self.l2 = torch.nn.Linear(512, 256)
self.l3 = torch.nn.Linear(256, 128)
self.l4 = torch.nn.Linear(128, 64)
self.l5 = torch.nn.Linear(64, 10)
def forward(self, x):
x = x.view(-1, 784)
x = F.relu(self.l1(x))
x = F.relu(self.l2(x))
x = F.relu(self.l3(x))
x = F.relu(self.l4(x))
return self.l5(x)
model = Net()
# --------------------------------------------------
criterion = torch.nn.CrossEntropyLoss()
# momentum是冲量，可以从局部极值走出来尽可能找到全局最优解
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
# --------------------------------------------------
def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data
# print(target)
optimizer.zero_grad()
# forward + backward + update
outputs = model(inputs)
# print(outputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_idx % 300 == 299:
print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
running_loss = 0.0
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images, labels = data
outputs = model(images)
# print(outputs)
_, predicted = torch.max(outputs.data, dim=1)
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(10):
train(epoch)
test()
2. CNN实现
注：经过卷积后的图像长宽计算公式如下
h e i g h t o u t = ( h e i g h t i n − h e i g h t k e r n e l + 2 × p a d d i n g ) s t r i d e + 1 height_{out} =\frac{(height_{in}-height_{kernel}+2\times{padding})}{stride} +1 heightout=stride(heightin−heightkernel+2×padding)+1
w i d t h o u t = ( w i d t h i n − w i d t h t k e r n e l + 2 × p a d d i n g ) s t r i d e + 1 width_{out} =\frac{(width_{in}-widtht_{kernel}+2\times{padding})}{stride} +1 widthout=stride(widthin−widthtkernel+2×padding)+1
代码如下（示例）：
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
batch_size = 64
# transforms.ToTensor()：Covert the PIL Image to Tensor
# transforms.Normalize:The PARAMETERS are mean and std respectively,It use formulation x=(x-mean)/std
transform = transforms.Compose([transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])
train_dataset = datasets.MNIST(root='./dataset/mnist/',
train=True,
download=True,
transform=transform)
train_loader = DataLoader(train_dataset,
shuffle=True,
batch_size=batch_size)
test_dataset = datasets.MNIST(root='./dataset/mnist/',
train=False,
download=True,
transform=transform)
test_loader = DataLoader(test_dataset,
shuffle=False,
batch_size=batch_size)
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
# self.l1 = torch.nn.Linear(784, 512)
# self.l2 = torch.nn.Linear(512, 256)
# self.l3 = torch.nn.Linear(256, 128)
# self.l4 = torch.nn.Linear(128, 64)
# self.l5 = torch.nn.Linear(64, 10)
self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=(5, 5))
self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=(5, 5))
self.pooling = torch.nn.MaxPool2d(2)
self.fc = torch.nn.Linear(320, 10)
def forward(self, x):
# x = x.view(-1, 784)
# x = F.relu(self.l1(x))
# x = F.relu(self.l2(x))
# x = F.relu(self.l3(x))
# x = F.relu(self.l4(x))
# return self.l5(x)
# Flatten data from (n, 1, 28, 28) to (n, 784)
# print(x.shape)
batch_size = x.size(0)
x = F.relu(self.pooling(self.conv1(x)))
# print(x.shape)
x = F.relu(self.pooling(self.conv2(x)))
# print(x.shape)
x = x.view(batch_size, -1) # flatten
# print(x.shape)
x = self.fc(x)
return x
model = Net()
# --------------------------------------------------
criterion = torch.nn.CrossEntropyLoss()
# momentum是冲量，可以从局部极值走出来尽可能找到全局最优解
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
# --------------------------------------------------
def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data
# print(target)
optimizer.zero_grad()
# forward + backward + update
outputs = model(inputs)
# print(outputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_idx % 300 == 299:
print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
running_loss = 0.0
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images, labels = data
outputs = model(images)
# print(outputs)
_, predicted = torch.max(outputs.data, dim=1)
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(10):
train(epoch)
test()