卷積神經網絡CNN
import torch
import torch.nn as nn
from torch.autograd import Variable
import matplotlib.pyplot as plt
import torch.utils.data as Data
import torchvision
# 下載MNIST數據集
# 若已有該數據集,需改爲DOWNLOAD_MNIST = False
DOWNLOAD_MNIST = True
train_data = torchvision.datasets.MNIST(
root='./mnist',
train=True,
transform=torchvision.transforms.ToTensor(),
download = DOWNLOAD_MNIST
)
test_data = torchvision.datasets.MNIST(root='./mnist/',train=False)
with torch.no_grad():
test_x = Variable(torch.unsqueeze(test_data.data, dim=1)).type(torch.FloatTensor).cuda()
test_y = test_data.targets[:10000].cuda()
# 配置批處理
train_loader = Data.DataLoader(
dataset=train_data,
batch_size=50,
shuffle=True,
num_workers=3
)
# CNN網絡
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
# 第一個卷積層
self.conv1 = nn.Sequential(
nn.Conv2d(# 原圖(1, 28, 28)
in_channels=1,
out_channels=16,
kernel_size=5,
stride=1,
padding=2 # (kernel_size-1)/2
),# (1, 28, 28) -> (16, 28, 28)
nn.ReLU(),
nn.MaxPool2d(kernel_size=2) # (16, 28, 28) -> (16, 14, 14)
)
# 第二個卷積層
self.conv2 = nn.Sequential(
nn.Conv2d(16, 32, 5, 1, 2),
nn.ReLU(),
nn.MaxPool2d(2)
)# (16, 14, 14) -> (32, 7, 7)
self.out = nn.Linear(32 * 7 * 7, 10)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = x.view(x.size(0), -1)
output = self.out(x)
return output
cnn = CNN().cuda()
# 配置網絡優化器
optimizer = torch.optim.Adam(cnn.parameters(), lr = 0.001)
loss_func = nn.CrossEntropyLoss()
plt.ion()
plt.show()
plt.figure()
steplist = []
losslist = []
accuracylist = []
for epoch in range(1):
for step, (x, y) in enumerate(train_loader):
b_x = Variable(x).cuda()
b_y = Variable(y).cuda()
output = cnn(b_x)
loss = loss_func(output, b_y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if step % 10 == 0:
test_output = cnn(test_x[:10000])
pred_y = torch.max(test_output, 1)[1].cpu().data.numpy().squeeze()
accuracy = sum(pred_y == test_y.cpu().numpy()) / test_y.size(0)
print('Epoch:', epoch, ' | train loss:%.4f'%loss.item(), ' | test accuracy:%.2f'%accuracy)
steplist.append(step)
losslist.append(loss.item())
accuracylist.append(accuracy)
plt.subplot(121)
plt.title('loss')
plt.plot(steplist, losslist, 'r-', lw=1)
plt.subplot(122)
plt.title('accuracy')
plt.plot(steplist, accuracylist, 'b-', lw=1)
plt.pause(0.1)
plt.ioff()
plt.show()
結果:
Epoch: 0 | train loss:1.4696 | test accuracy:0.69
Epoch: 0 | train loss:0.7815 | test accuracy:0.80
Epoch: 0 | train loss:0.5405 | test accuracy:0.79
...
Epoch: 0 | train loss:0.0603 | test accuracy:0.98
Epoch: 0 | train loss:0.0451 | test accuracy:0.98
Epoch: 0 | train loss:0.0594 | test accuracy:0.98
可以看到,CNN對MNIST數據集的預測能達到98%的準確率,這是一個相當好的結果
整個預測的可視化過程:
循環神經網絡RNN
import torch
import torch.nn as nn
from torch.autograd import Variable
import matplotlib.pyplot as plt
import torch.utils.data as Data
import torchvision
DOWNLOAD_MNIST = True
train_data = torchvision.datasets.MNIST(
root='./mnist',
train=True,
transform=torchvision.transforms.ToTensor(),
download = DOWNLOAD_MNIST
)
train_loader = Data.DataLoader(
dataset=train_data,
batch_size=64,
shuffle=True,
)
test_data = torchvision.datasets.MNIST(root='./mnist/',train=False)
with torch.no_grad():
test_x = (torch.unsqueeze(test_data.data, dim=1).type(torch.FloatTensor)/255.).cuda()
test_y = test_data.targets[:10000].cuda()
class RNN(nn.Module):
def __init__(self):
super(RNN, self).__init__()
self.rnn = nn.LSTM(
input_size=28,
hidden_size=64,
num_layers=1,
batch_first=True
)
self.out = nn.Linear(64, 10)
def forward(self, x):
r_out, (h_n, h_c) = self.rnn(x, None)
out = self.out(r_out[:, -1, :]) # (batch, time_step[-1], input_size)
return out
rnn = RNN().cuda()
optimizer = torch.optim.Adam(rnn.parameters(), lr = 0.001)
loss_func = nn.CrossEntropyLoss()
plt.ion()
plt.show()
plt.figure()
steplist = []
losslist = []
accuracylist = []
for epoch in range(1):
for step, (x, y) in enumerate(train_loader):
b_x = Variable(x.view(-1, 28, 28)).cuda()
b_y = Variable(y).cuda()
output = rnn(b_x)
loss = loss_func(output, b_y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if step % 10 == 0:
test_output = rnn(test_x[:10000].view(-1, 28, 28))
pred_y = torch.max(test_output, 1)[1].cpu().data.numpy().squeeze()
accuracy = sum(pred_y == test_y.cpu().numpy()) / test_y.size(0)
print('Epoch:', epoch, ' | train loss:%.4f'%loss.item(), ' | test accuracy:%.2f'%accuracy)
steplist.append(step)
losslist.append(loss.item())
accuracylist.append(accuracy)
plt.subplot(121)
plt.title('loss')
plt.plot(steplist, losslist, 'r-', lw=1)
plt.subplot(122)
plt.title('accuracy')
plt.plot(steplist, accuracylist, 'b-', lw=1)
plt.pause(0.1)
plt.ioff()
plt.show()
test_output = rnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].cpu().data.numpy().squeeze()
print(pred_y, 'prediction number')
print(test_y[:10].cpu().numpy(), 'real number')
結果:
Epoch: 0 | train loss:2.2996 | test accuracy:0.13
Epoch: 0 | train loss:2.2977 | test accuracy:0.15
Epoch: 0 | train loss:2.2768 | test accuracy:0.21
...
Epoch: 0 | train loss:0.1875 | test accuracy:0.94
Epoch: 0 | train loss:0.2653 | test accuracy:0.94
Epoch: 0 | train loss:0.3055 | test accuracy:0.94