pytorch初体验
实例:数字识别
代码部分:
``
import torch
from torch import nn, relu # 完成神经网络的相关工作
from torch import optim
import torchvision
from matplotlib import pyplot as plt
from torch.nn.functional import mse_loss
from utils import plot_image,plot_curve,one_hot
batch_size=512
#1、加载训练数据集
train_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST('mnist_data', train=True, download=True,#如果文件不存在那么就从网上下载;trian:数据是用来训练的
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(#图片标准化,性能提升,使数据在0周围,如果去掉这行代码会使性能变差
(0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=True)
#一次取多少张图片,去的时候要随机打散(shuffle)
#加载测试数据集
test_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST('mnist_data/', train=False, download=True,
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(
(0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=False)
x,y=next(iter(train_loader))
print(x.shape,y.shape,x.min(),x.max())
#plot_image(x,y,'image sample')
#加载数据完毕
#2、创建网络
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
#wx+b
self.fc1=nn.Linear(28*28,256)#256为随即决定的
self.fc2=nn.Linear(256,64)
self.fc3=nn.Linear(64,10)
def forward(self,x):
# x:[b,1,28,28]
#h1=relu(xw+b)
x=relu(self.fc1(x))
#h2=relu(xw+b)
x=relu(self.fc2(x))
#最后一层可加可不加激活函数,并使用均方差
#h3=h2w3+b3
x=self.fc3(x)
return x
#网络初始化
net=Net()
train_loss=[]
#优化器
optimzer=optim.SGD(net.parameters(),lr=0.01,momentum=0.9)
for epoch in range(3):#整个数据集迭代三次
#整个数据集全部迭代
for batch_idx,(x,y) in enumerate(train_loader):
#x:[b,1,28,28],y:[512],对数据进行重组,符合网络输入的格式
x=x.view(x.size(0),28*28)
#=>[b,10]
out=net(x)
#[b,10]
y_onehot=one_hot(y)
#loss=mse(out,y_out)
loss=mse_loss(out,y_onehot)
#清零
optimzer.zero_grad()
#w'=w-lr*grad
loss.backward()
optimzer.step()
train_loss.append(loss.item())
if batch_idx%10==0:
print(epoch,batch_idx,loss.item())
#我们这个时候会得到一个比较好的[w1,b1,w2,b2,w3,b3]
total_correct=0
plot_curve(train_loss)
#做一个准确度测试
for x,y in test_loader:
x=x.view(x.size(0),28*28)
out=net(x)
#得到第一维度存在最大值的索引
pred=out.argmax(dim=1)
correct=pred.eq(y).sum().float().item()
total_correct+=correct
total_num=len(test_loader.dataset)
acc=total_correct/total_num
print("test acc:",acc)
#测试数据集
x,y=next(iter(test_loader))
out=net(x.view(x.size(0),28*28))
pred =out.argmax(dim=1)
plot_image(x,pred,'test')
```python
在这里插入代码片
辅助函数:
`import torch
from matplotlib import pyplot as plt
#画下降曲线
def plot_curve(data):
fig = plt.figure()
plt.plot(range(len(data)), data, color='blue')
plt.legend(['value'], loc='upper right')
plt.xlabel('step')
plt.ylabel('value')
plt.show()
def plot_image(img, label, name):
fig = plt.figure()
for i in range(6):
plt.subplot(2, 3, i + 1)
plt.tight_layout()
plt.imshow(img[i][0]*0.3081+0.1307, cmap='gray', interpolation='none')
plt.title("{}: {}".format(name, label[i].item()))
plt.xticks([])
plt.yticks([])
plt.show()
def one_hot(label, depth=10):
out = torch.zeros(label.size(0), depth)
idx = torch.LongTensor(label).view(-1, 1)
out.scatter_(dim=1, index=idx, value=1)
return out`