pytorch MNIST手写体识别 pytorch实现MNIST手写体识别

import torch
import torch.nn as nn
import torchvision #这里面直接加载MNIST数据的方法
import torchvision.transforms as transforms # 将数据转为Tensor
import torch.optim as optim 
import torch.utils.data.dataloader as dataloader

train_set = torchvision.datasets.MNIST(
 root='./data', # 文件存储位置
 train=True,
 transform=transforms.ToTensor(),
 download=True
)

train_dataloader = dataloader.DataLoader(dataset=train_set,shuffle=False,batch_size=100)# dataset可以省

'''
dataloader返回（images,labels）
其中，
images维度：[batch_size,1,28,28]
labels：[batch_size]，即图片对应的
'''

test_set = torchvision.datasets.MNIST(
 root='./data',
 train=False,
 transform=transforms.ToTensor(),
 download=True
)

test_dataloader = dataloader.DataLoader(test_set,batch_size=100,shuffle=False) # dataset可以省

class NeuralNet(nn.Module):
 def __init__(self,in_num,h_num,out_num):
 super(NeuralNet,self).__init__()
 self.ln1 = nn.Linear(in_num,h_num)
 self.ln2 = nn.Linear(h_num,out_num)
 self.relu = nn.ReLU()
 
 def forward(self,x):
 return self.ln2(self.relu(self.ln1(x)))

in_num = 784 # 输入维度
h_num = 500 # 隐藏层维度
out_num = 10 # 输出维度
epochs = 30 # 迭代次数
learning_rate = 0.001
USE_CUDA = torch.cuda.is_available() # 定义是否可以使用cuda

model = NeuralNet(in_num,h_num,out_num) # 初始化模型
optimizer = optim.Adam(model.parameters(),lr=learning_rate) # 使用Adam
loss_fn = nn.CrossEntropyLoss() # 损失函数

for e in range(epochs):
 for i,data in enumerate(train_dataloader):
 (images,labels) = data
 images = images.reshape(-1,28*28) # [batch_size,784]
 if USE_CUDA:
  images = images.cuda() # 使用cuda
  labels = labels.cuda() # 使用cuda
  
 y_pred = model(images) # 预测
 loss = loss_fn(y_pred,labels) # 计算损失
 
 optimizer.zero_grad()
 loss.backward()
 optimizer.step()
 
 n = e * i +1
 if n % 100 == 0:
  print(n,'loss:',loss.item())

with torch.no_grad():
 total = 0
 correct = 0
 for (images,labels) in test_dataloader:
 images = images.reshape(-1,28*28)
 if USE_CUDA:
  images = images.cuda()
  labels = labels.cuda()
  
 result = model(images)
 prediction = torch.max(result, 1)[1] # 这里需要有[1]，因为它返回了概率还有标签
 total += labels.size(0)
 correct += (prediction == labels).sum().item()
 
 print("The accuracy of total {} images: {}%".format(total, 100 * correct/total))