步骤:
1.加载图片
2.建立模型
3.训练
4.预测
辅助函数,建立utils.py文件方便调用
from matplotlib import pyplot as plt
import torch
# 下降曲线绘制
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()
# 图片识别
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()
# 实现one_hot的编码
def one_hot(label,depth=10):
out=torch.zeros(label.size(0),depth)
idx=torch.LongStorage(label).view(-1,1)
out.scatter_(dim=1,index=idx,value=1)
return out
通过
1.加载图片
2.建立模型
3.训练
4.预测
编写代码
import torch
from bdong.utils import plot_image
import torch
from torch import nn
from torch.nn import functional as F
from torch import optim
import torchvision
from torch.nn.functional import one_hot
from utils import plot_curve,plot_image
# 并行处理图片大大节省计算时间,一次处理图片的数量
batch_size = 512
#step.1加载数据集load datas
# step1. load dataset
# 加载数据集,train表示测试还是训练,download为True表示没有这个数据会去网上去下载
# torchvision.transforms.ToTensor()数据转化
# torchvision.transforms.Normalize((0.1307,), (0.3081,))均匀分布在0附近
# shuffle=True随机打散
train_loader = torch.utils.data.DataLoader(
torchvision.datasets.MNIST('mnist_data', train=True, download=True,
transform=torchvision.transforms.Compose([
torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize(
(0.1307,), (0.3081,))
])),
batch_size=batch_size, shuffle=True)
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')
# Step2.
# 构建网络
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(28 * 28, 256)
self.fc2 = nn.Linear(256, 64)
self.fc3 = nn.Linear(64, 10)
def forward(self, x):
# img : [batch,1,28,28]
# x : [batch,784]
# h1 = relu(xw1 + b1)
x = F.relu(self.fc1(x))
# h2 = relu(h1w2 + b2)
x = F.relu(self.fc2(x))
# h3 = h2w3 + b3
x = self.fc3(x)
return x
# step3.
# 训练训练样本
net = Net()
# [w1,b1,w2,b2,w3,b3]
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)
train_loss = []
for epoch in range(3):
for batch_idx, (x, y) in enumerate(train_loader):
# x : [batch,1,28,28] y:[batch]
# flatten [batch,1,28,28] - > [batch,feature]
# x : [batch,784]
x = x.view(x.size(0), 28 * 28)
out = net(x)
# one-hot
y_onehot = one_hot(y,10)
y_onehot=y_onehot.float()
# loss : mse(out,y_onehot)
loss = F.mse_loss(out, y_onehot)
# 清零梯度
optimizer.zero_grad()
# 计算梯度
loss.backward()
# 更新梯度
# w' = w - lr * grad
optimizer.step()
train_loss.append(loss.item())
if batch_idx % 10 == 0:
print(f"epoch:{epoch} step:{batch_idx} loss:{loss.item()}")
plot_curve(train_loss)
# we get optimal [w1,b1,w2,b2,w3,b3]
# Step4.
# 测试集验证
total_correct=0
for x,y in test_loader:
x=x.view(x.size(0),28*28)
out=net(x)
# out[b,10]=>pred:[b]
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)
# 拿到一个test中的图片
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')