Pytorch_cnn_net实现mnist手写识别

导入函数库

import torch
import torchvision
import torch.nn as nn
from torch.autograd import Variable
import torch.untils.data as Data
import matlibplot.pyplot as plt

参数设置

EPOCH=1#训练一次
BATCH_SIZE=50#分组训练每次训练50个
LR=0.001#学习速度为0.001
DOWNLOAD_MNIST=False#已经下载完毕

训练的数据

train_data = torchvision.datasets.MNIST(
    root='./mnist/',    # 保存或者提取位置
    train=True,  # this is training data
    transform=torchvision.transforms.ToTensor(),    # 转换 PIL.Image or numpy.ndarray 成
                                                    # torch.FloatTensor (C x H x W), 训练的时候 normalize 成 [0.0, 1.0] 区间
    download=DOWNLOAD_MNIST,          # 没下载就下载, 下载了就不用再下了
)

输出图片样例，以及训练数据的类型格式

print(train_data.train_data.size())
print(train_data.train_labels.size())
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i'% train_data.train_labels[0])
plt.show()

说明有60000组数据，每组数据的格式为28*28

torch.Size([60000, 28, 28])
torch.Size([60000])

手写图片为

数据载体

train_loader=Data.DataLoader(dataset=train_data,
			     batch_size=BATCH_SIZE,
			     shuffle=True,
			     num_workers=2)
	#其中dataset为所需要处理的数据，batch_size每次处理所需要的规格，
	shuffle随机处理，num_workers=2双线程

test_data=torchvision.dataset.MNIST(root='./mnist/',train=False)
test_x=Variable(torch.unsqueeze(test_data.test_data,dim=1),volatile=True).type(torch.FloatTensor)[:2000]/255.#图片中的数据化为可以处理的Variable,
test_y=test_data.test_label[:2000]#所代表的数据设置为test_y

搭建CNN网络

class CNN(nn.Module):
	def __init__(self):
		super(CNN,self).__init__()
		self.conv1=nn.Sequential(
		nn.Conv2d(
			in_channels=1,
			out_channels=16,#16个扫描片同时扫描
			kernel_size=5,#5*5扫描
			stride=1,#步长
			padding=2,#加的周围空白
			#if stride=1,padding=(kernel_size-1)/2=2,围上了一圈0，黑色，255白色
),#卷积层，过滤器
		nn.ReLU(),#网络
		nn.MacPool2d(
		kernel_size=2,
		),#池化层
		)
		self.conv2=nn.Sequential(
		nn.Conv2d=(16,32,5,1,2),
		nn.ReLU(),
		nn.MaxPool2d(2),
		)
		self.out=nn.Linear(32*7*7,10)#三维数据展平
		def forward(self,x):
		x=self.conv1(x),
		x=self.conv2(x),#(batch,32,7,7)
		x=x.view(x.size(0),-1)#(batch,32*7*7)
		output=self.out(x)
		return output
cnn=CNN()
print(cnn)

输出网络格式

CNN(
  (conv1): Sequential(
    (0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU()
    (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (conv2): Sequential(
    (0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU()
    (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (out): Linear(in_features=1568, out_features=10, bias=True)
)

优化器

optimizer=torch.optimAdam()
loss_fuc=nn.CrossEntropyLoss()

开始训练

if __name__='__main__':
	for epoch in range(EPOCH):
		for step,(x,y) in enumerate(train_loader):
			b_x=Variable(x)
			b_y=Variable(y)
			output=cnn(x)
			loss=loss_func(output,b_y)
			optimizer.zero_grad()
			loss.backward()
			optimizer.step()
			if step%50==0:
				test_output=cnn(test_x)
   				pred_y = torch.max(test_output, 1)[1].data.squeeze()
 				accuracy = sum(pred_y == test_y) / test_y.size(0)
    				print('Epoch: ', epoch, '| train loss: %.4f' % loss.item(), '| test accuracy: %.4f'% accuracy.data.numpy())

训练成功之后，查看前十个数字以及其预估值的比较

test_output = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
#torch.max(a,1) 返回每一行中最大值的那个元素，且返回其索引
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')