标签:figure 代码 log squeeze class 图像 none lse maps
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import matplotlib.pyplot as plt
import numpy
# 一个函数,用来计算模型中有多少参数
def get_n_params(model):
np=0
for p in list(model.parameters()):
np += p.nelement()
return np
# 使用GPU训练,可以在菜单 "代码执行工具" -> "更改运行时类型" 里进行设置
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
1.加载数据 (MNIST)
torchvision.datasets.MNIST(root, train=True, transform=None, target_transform=None, download=False)
input_size = 28*28 # MNIST上的图像尺寸是 28x28
output_size = 10 # 类别为 0 到 9 的数字,因此为十类
train_loader = torch.utils.data.DataLoader(
datasets.MNIST(‘./data‘, train=True, download=True,
transform=transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])),
batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST(‘./data‘, train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])),
batch_size=1000, shuffle=True)
#显示数据集中的部分图像
plt.figure(figsize=(8, 5))
for i in range(20):
plt.subplot(4, 5, i + 1)
image, _ = train_loader.dataset.__getitem__(i)
plt.imshow(image.squeeze().numpy(),‘gray‘)
plt.axis(‘off‘);
2.创建网络
class FC2Layer(nn.Module):
def __init__(self, input_size, n_hidden, output_size):
super(FC2Layer, self).__init__()
self.input_size = input_size
# 这里直接用 Sequential 就定义了网络,注意要和下面 CNN 的代码区分开
self.network = nn.Sequential(
nn.Linear(input_size, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, output_size),
nn.LogSoftmax(dim=1)
)
def forward(self, x):
x = x.view(-1, self.input_size)
return self.network(x)
class CNN(nn.Module):
def __init__(self, input_size, n_feature, output_size):
super(CNN, self).__init__()
self.n_feature = n_feature
self.conv1 = nn.Conv2d(in_channels=1, out_channels=n_feature, kernel_size=5)
self.conv2 = nn.Conv2d(n_feature, n_feature, kernel_size=5)
self.fc1 = nn.Linear(n_feature*4*4, 50)
self.fc2 = nn.Linear(50, 10)
# 下面的 forward 函数,定义了网络的结构,按照一定顺序,把上面构建的一些结构组织起来
# 意思就是,conv1, conv2 等等的,可以多次重用
def forward(self, x, verbose=False):
x = self.conv1(x)
x = F.relu(x)
x = F.max_pool2d(x, kernel_size=2)
x = self.conv2(x)
x = F.relu(x)
x = F.max_pool2d(x, kernel_size=2)
x = x.view(-1, self.n_feature*4*4)
x = self.fc1(x)
x = F.relu(x)
x = self.fc2(x)
x = F.log_softmax(x, dim=1)
return x
#定义训练和测试函数
# 训练函数
def train(model):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
# 把数据送到GPU中
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print(‘Train: [{}/{} ({:.0f}%)]\tLoss: {:.6f}‘.format(
batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
#测试函数
def test(model):
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
# 把数据送到GPU中
data, target = data.to(device), target.to(device)
# 把数据送入模型,得到预测结果
output = model(data)
# 计算本次batch的损失,并加到 test_loss 中
test_loss += F.nll_loss(output, target, reduction=‘sum‘).item()
# get the index of the max log-probability,最后一层输出10个数,
# 值最大的那个即对应着分类结果,然后把分类结果保存在 pred 里
pred = output.data.max(1, keepdim=True)[1]
# 将 pred 与 target 相比,得到正确预测结果的数量,并加到 correct 中 correct += pred.eq(target.data.view_as(pred)).cpu().sum().item()
test_loss /= len(test_loader.dataset)
accuracy = 100. * correct / len(test_loader.dataset)
print(‘\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n‘.format(
test_loss, correct, len(test_loader.dataset),
accuracy))
n_hidden = 8 # number of hidden units
model_fnn = FC2Layer(input_size, n_hidden, output_size)
model_fnn.to(device)
optimizer = optim.SGD(model_fnn.parameters(), lr=0.01, momentum=0.5)
print(‘Number of parameters: {}‘.format(get_n_params(model_fnn)))
train(model_fnn)
test(model_fnn)
4.在卷积神经网络上训练
# Training settings
n_features = 6 # number of feature maps
model_cnn = CNN(input_size, n_features, output_size)
model_cnn.to(device)
optimizer = optim.SGD(model_cnn.parameters(), lr=0.01, momentum=0.5)
print(‘Number of parameters: {}‘.format(get_n_params(model_cnn)))
train(model_cnn)
test(model_cnn)
5.打乱像素顺序再次在两个网络上训练与测试
perm = torch.randperm(784)
plt.figure(figsize=(8, 4))
for i in range(10):
image, _ = train_loader.dataset.__getitem__(i)
# permute pixels
image_perm = image.view(-1, 28*28).clone()
image_perm = image_perm[:, perm]
image_perm = image_perm.view(-1, 1, 28, 28)
plt.subplot(4, 5, i + 1)
plt.imshow(image.squeeze().numpy(), ‘gray‘)
plt.axis(‘off‘)
plt.subplot(4, 5, i + 11)
plt.imshow(image_perm.squeeze().numpy(), ‘gray‘)
plt.axis(‘off‘)
# 对每个 batch 里的数据,打乱像素顺序的函数
def perm_pixel(data, perm):
# 转化为二维矩阵
data_new = data.view(-1, 28*28)
# 打乱像素顺序
data_new = data_new[:, perm]
# 恢复为原来4维的 tensor
data_new = data_new.view(-1, 1, 28, 28)
return data_new
# 训练函数
def train_perm(model, perm):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
# 像素打乱顺序
data = perm_pixel(data, perm)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print(‘Train: [{}/{} ({:.0f}%)]\tLoss: {:.6f}‘.format(
batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
# 测试函数
def test_perm(model, perm):
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
data, target = data.to(device), target.to(device)
# 像素打乱顺序
data = perm_pixel(data, perm)
output = model(data)
test_loss += F.nll_loss(output, target, reduction=‘sum‘).item()
pred = output.data.max(1, keepdim=True)[1]
correct += pred.eq(target.data.view_as(pred)).cpu().sum().item()
test_loss /= len(test_loader.dataset)
accuracy = 100. * correct / len(test_loader.dataset)
print(‘\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n‘.format(
test_loss, correct, len(test_loader.dataset),
accuracy))
#在全连接网络上训练与测试:
perm = torch.randperm(784)
n_hidden = 8 # number of hidden units
model_fnn = FC2Layer(input_size, n_hidden, output_size)
model_fnn.to(device)
optimizer = optim.SGD(model_fnn.parameters(), lr=0.01, momentum=0.5)
print(‘Number of parameters: {}‘.format(get_n_params(model_fnn)))
train_perm(model_fnn, perm)
test_perm(model_fnn, perm)
#在卷积神经网络上训练与测试
perm = torch.randperm(784)
n_features = 6 # number of feature maps
model_cnn = CNN(input_size, n_features, output_size)
model_cnn.to(device)
optimizer = optim.SGD(model_cnn.parameters(), lr=0.01, momentum=0.5)
print(‘Number of parameters: {}‘.format(get_n_params(model_cnn)))
train_perm(model_cnn, perm)
test_perm(model_cnn, perm)
标签:figure 代码 log squeeze class 图像 none lse maps
原文地址:https://www.cnblogs.com/lixinhh/p/13414333.html