Pytorch--ResNet识别MNIST数据集
程序员文章站
2022-07-14 20:23:02
...
之前搭建了ResNet网络架构,所以用其识别MNIST数据集。
1、由于电脑的运行内存,在设计网络结构时,用了8层网络,分别是1个输入层,1个输出层,三个Block,每个Block中有1个Basicblock,每个Basicblock中有2层layer。
2、考虑到MNIST的数据集的大小为28 x 28,没经过第2个和都3个Block,大小都减半,也就是说,进入输出层时的大小为7 x 7,所以在最后用到的Average_pool的大小为7。
3、因为MNIST的channel数为1,所以in_channel = 1.
import torch
import torchvision
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.data as Data
import matplotlib.pyplot as plt
# define hyper parameters
Batch_size = 50
Lr = 0.1
Epoch = 1
# define train set and test set
train_dataset = torchvision.datasets.MNIST(
root='./MNIST',
train=True,
download=True,
transform=torchvision.transforms.ToTensor()
)
test_dataset = torchvision.datasets.MNIST(
root='./MNISt',
train=False,
download=True,
transform=torchvision.transforms.ToTensor()
)
# define train loader
train_loader = Data.DataLoader(
dataset=train_dataset,
shuffle=True,
batch_size=Batch_size
)
test_x = torch.unsqueeze(test_dataset.data, dim=1).type(torch.Tensor)
test_y = test_dataset.targets
# print(test_y.shape, test_x.shape)
# construct network
class Basicblock(nn.Module):
def __init__(self, in_planes, planes, stride=1):
super(Basicblock, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(in_channels=in_planes, out_channels=planes, kernel_size=3, stride=stride, padding=1, bias=False),
nn.BatchNorm2d(planes),
nn.ReLU()
)
self.conv2 = nn.Sequential(
nn.Conv2d(in_channels=planes, out_channels=planes, kernel_size=3, stride=1, padding=1, bias=False),
nn.BatchNorm2d(planes),
)
if stride != 1 or in_planes != planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_channels=in_planes, out_channels=planes, kernel_size=3, stride=stride, padding=1),
nn.BatchNorm2d(planes)
)
else:
self.shortcut = nn.Sequential()
def forward(self, x):
out = self.conv1(x)
out = self.conv2(out)
out += self.shortcut(x)
out = F.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, num_block, num_classes):
super(ResNet, self).__init__()
self.in_planes = 16
self.conv1 = nn.Sequential(
nn.Conv2d(in_channels=1, out_channels=16, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(16),
nn.ReLU()
)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
self.block1 = self._make_layer(block, 16, num_block[0], stride=1)
self.block2 = self._make_layer(block, 32, num_block[1], stride=2)
self.block3 = self._make_layer(block, 64, num_block[2], stride=2)
# self.block4 = self._make_layer(block, 512, num_block[3], stride=2)
self.outlayer = nn.Linear(64, num_classes)
def _make_layer(self, block, planes, num_block, stride):
layers = []
for i in range(num_block):
if i == 0:
layers.append(block(self.in_planes, planes, stride))
else:
layers.append(block(planes, planes, 1))
self.in_planes = planes
return nn.Sequential(*layers)
def forward(self, x):
x = self.maxpool(self.conv1(x))
x = self.block1(x) # [200, 64, 28, 28]
x = self.block2(x) # [200, 128, 14, 14]
x = self.block3(x) # [200, 256, 7, 7]
# out = self.block4(out)
x = F.avg_pool2d(x, 7) # [200, 256, 1, 1]
x = x.view(x.size(0), -1) # [200,256]
out = self.outlayer(x)
return out
ResNet18 = ResNet(Basicblock, [1, 1, 1, 1], 10)
# print(ResNet18)
opt = torch.optim.SGD(ResNet18.parameters(), lr=Lr)
loss_fun = nn.CrossEntropyLoss()
a = []
ac_list = []
for epoch in range(Epoch):
for i, (x, y) in enumerate(train_loader):
output = ResNet18(x)
loss = loss_fun(output, y)
opt.zero_grad()
loss.backward()
opt.step()
if i % 100 == 0:
a.append(i)
test_output = torch.max(ResNet18(test_x), dim=1)[1]
loss = loss_fun(ResNet18(test_x), test_y).item()
accuracy = torch.sum(torch.eq(test_y, test_output)).item() / test_y.numpy().size
ac_list.append(accuracy)
print('Epoch:', Epoch, '|loss%.4f' % loss, '|accuracy%.4f' % accuracy)
print('real value', test_y[: 10].numpy())
print('train value', torch.max(ResNet18(test_x)[: 10], dim=1)[1].numpy())
plt.plot(a, ac_list, color='r')
plt.show()
最后的结果为:
Epoch: 1 |loss2.3029 |accuracy0.1889
Epoch: 1 |loss0.5059 |accuracy0.8985
Epoch: 1 |loss0.2568 |accuracy0.9426
Epoch: 1 |loss0.1445 |accuracy0.9651
Epoch: 1 |loss0.1147 |accuracy0.9697
Epoch: 1 |loss0.0960 |accuracy0.9741
Epoch: 1 |loss0.0919 |accuracy0.9750
Epoch: 1 |loss0.0739 |accuracy0.9789
Epoch: 1 |loss0.0719 |accuracy0.9802
Epoch: 1 |loss0.0593 |accuracy0.9836
Epoch: 1 |loss0.0621 |accuracy0.9816
Epoch: 1 |loss0.0575 |accuracy0.9834
real value [7 2 1 0 4 1 4 9 5 9]
train value [7 2 1 0 4 1 4 9 5 9]
在测试集上的精确度:
上一篇: typescript 接口使用
下一篇: 一个关于常用类的简单小练习
推荐阅读
-
基于MNIST手写数字数据集的数字识别小程序
-
python MNIST手写识别数据调用API的方法
-
基于jupyter notebook的python编程(Win10通过OpenCv-3.4.1进行人脸口罩数据集的模型训练并进行戴口罩识别检测)
-
mnist数据集下载及相关配置
-
tensorflow实现加载mnist数据集
-
pytorch 把MNIST数据集转换成图片和txt的方法
-
Tensorflow机器学习入门——MINIST数据集识别
-
应用SVM对MNIST数据集进行分类
-
pytorch实现建立自己的数据集(以mnist为例)
-
深度学习 从零开始 —— 神经网络数学基础(一),学习Keras库的使用,神经网络简单流程,MNIST数据集使用