利用torchvision.datasets函数可以在线导入pytorch中的数据集,包含一些常见的数据集如MNIST、CIFAR-10等。本次使用的是CIFAR10数据集,也是一个很经典的图像分类数据集,由 Hinton 的学生 Alex Krizhevsky 和 Ilya Sutskever 整理的一个用于识别普适物体的小型数据集,一共包含 10 个类别的 RGB 彩色图片。
PyTorch的CIFAR-10数据集有时下载不了,我这里将下载好的压缩包放在网盘中,需要的可以自行下载,解压后放在当前项目文件的data文件夹下。链接:https://pan.baidu.com/s/1NBHp0SxEOJ5EIyYUsDHm_g
提取码:qp3k
LeNet网络之前在我的博客详细讲解过:https://blog.csdn.net/muye_IT/article/details/123539199?spm=1001.2014.3001.5501
LeNet网络架构总览图:
model.py ——定义LeNet网络模型
# 使用torch.nn包来构建神经网络.
import torch.nn as nn
import torch.nn.functional as F
class LeNet(nn.Module): # 继承于nn.Module这个父类
def __init__(self): # 初始化网络结构
super(LeNet, self).__init__() # 多继承需用到super函数
self.conv1 = nn.Conv2d(3, 16, 5)
self.pool1 = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(16, 32, 5)
self.pool2 = nn.MaxPool2d(2, 2)
self.fc1 = nn.Linear(32*5*5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x): # 正向传播过程
x = F.relu(self.conv1(x)) # input(3, 32, 32) output(16, 28, 28)
x = self.pool1(x) # output(16, 14, 14)
x = F.relu(self.conv2(x)) # output(32, 10, 10)
x = self.pool2(x) # output(32, 5, 5)
x = x.view(-1, 32*5*5) # output(32*5*5)
x = F.relu(self.fc1(x)) # output(120)
x = F.relu(self.fc2(x)) # output(84)
x = self.fc3(x) # output(10)
return x
Conv2d、MaxPool2d、Linear在pytorch中对应的函数,以及函数参数的设置
常见的参数:
Conv2d ['stride', 'padding', 'dilation', 'groups','padding_mode', 'output_padding', 'in_channels','out_channels', 'kernel_size']
MaxPool2d('kernel_size', 'stride', 'padding', 'dilation','return_indices', 'ceil_mode')
Linear('in_features', 'out_features')
train.py ——加载数据集并训练,训练集计算loss,测试集计算accuracy,保存训练好的网络参数
import torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transforms
由shape (H x W x C) in the range [0, 255] → shape (C x H x W) in the range [0.0, 1.0]
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 导入50000张训练图片
train_set = torchvision.datasets.CIFAR10(root='./data', # 数据集存放目录
train=True, # 表示是数据集中的训练集
download=True, # 第一次运行时为True,下载数据集,下载完成后改为False
transform=transform) # 预处理过程
# 加载训练集,实际过程需要分批次(batch)训练
train_loader = torch.utils.data.DataLoader(train_set, # 导入的训练集
batch_size=50, # 每批训练的样本数
shuffle=False, # 是否打乱训练集
num_workers=0) # 使用线程数,在windows下设置为0
# 导入10000张测试图片
test_set = torchvision.datasets.CIFAR10(root='./data',
train=False, # 表示是数据集中的测试集
download=False,transform=transform)
# 加载测试集
test_loader = torch.utils.data.DataLoader(test_set,
batch_size=10000, # 每批用于验证的样本数
shuffle=False, num_workers=0)
# 获取测试集中的图像和标签,用于accuracy计算
test_data_iter = iter(test_loader)
test_image, test_label = test_data_iter.next()
使用下面语句可以在有GPU时使用GPU,无GPU时使用CPU进行训练
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
也可以直接指定
device = torch.device("cuda")
# 或者
# device = torch.device("cpu")
对应的,需要用to()函数来将Tensor在CPU和GPU之间相互移动,分配到指定的device中计算
import torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transforms
def main():
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 50000张训练图片
# 第一次使用时要将download设置为True才会自动去下载数据集
train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
download=False, transform=transform)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
shuffle=True, num_workers=0)
# 10000张验证图片
# 第一次使用时要将download设置为True才会自动去下载数据集
val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
download=False, transform=transform)
val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
shuffle=False, num_workers=0)
val_data_iter = iter(val_loader)
val_image, val_label = val_data_iter.next()
# classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
net = LeNet()
net.to(device) # 将网络分配到指定的device中
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
for epoch in range(5): # loop over the dataset multiple times
running_loss = 0.0
for step, data in enumerate(train_loader, start=0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs.to(device)) # 将inputs分配到指定的device中
loss = loss_function(outputs, labels.to(device)) # 将labels分配到指定的device中
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if step % 500 == 499: # print every 500 mini-batches
with torch.no_grad():
outputs = net(test_image.to(device)) # 将test_image分配到指定的device中
predict_y = torch.max(outputs, dim=1)[1]
accuracy = torch.eq(predict_y, val_label).sum().item() / val_label.size(0)
print('[%d, %5d] train_loss: %.3f test_accuracy: %.3f' %
(epoch + 1, step + 1, running_loss / 500, accuracy))
running_loss = 0.0
print('Finished Training')
save_path = './Lenet.pth'
torch.save(net.state_dict(), save_path)
if __name__ == '__main__':
main()
import torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transforms
def main():
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 50000张训练图片
# 第一次使用时要将download设置为True才会自动去下载数据集
train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
download=False, transform=transform)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
shuffle=True, num_workers=0)
# 10000张验证图片
# 第一次使用时要将download设置为True才会自动去下载数据集
val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
download=False, transform=transform)
val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
shuffle=False, num_workers=0)
val_data_iter = iter(val_loader)
val_image, val_label = val_data_iter.next()
# classes = ('plane', 'car', 'bird', 'cat',
# 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
net = LeNet()
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
for epoch in range(5): # loop over the dataset multiple times
running_loss = 0.0
for step, data in enumerate(train_loader, start=0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if step % 500 == 499: # print every 500 mini-batches
with torch.no_grad():
outputs = net(val_image) # [batch, 10]
predict_y = torch.max(outputs, dim=1)[1]
accuracy = torch.eq(predict_y, val_label).sum().item() / val_label.size(0)
print('[%d, %5d] train_loss: %.3f test_accuracy: %.3f' %
(epoch + 1, step + 1, running_loss / 500, accuracy))
running_loss = 0.0
print('Finished Training')
save_path = './Lenet.pth'
torch.save(net.state_dict(), save_path)
if __name__ == '__main__':
main()
predict.py——得到训练好的网络参数后,用自己找的图像进行分类测试,自己下载一张照片保存在根目录下,命名为1.jpg
import torch
import torchvision.transforms as transforms
from PIL import Image
from model import LeNet
def main():
transform = transforms.Compose(
[transforms.Resize((32, 32)),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
net = LeNet()
net.load_state_dict(torch.load('Lenet.pth'))
im = Image.open('1.jpg')#自己下载一张照片保存在根目录下,命名为1.jpg
im = transform(im) # [C, H, W]
im = torch.unsqueeze(im, dim=0) # [N, C, H, W]
with torch.no_grad():
outputs = net(im)
predict = torch.max(outputs, dim=1)[1].data.numpy()
print(classes[int(predict)])
if __name__ == '__main__':
main()