batch:一批·图像·数量
官方例子
#model
import torch.nn as nn
import torch.nn.functional as Fclass LeNet(nn.Module):def __init__(self):super(LeNet, self).__init__()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):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 ximport torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transformsdef 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=True, 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=True, 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 = next(val_data_iter)classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')net = LeNet()loss_function = nn.CrossEntropyLoss()#损失函数optimizer = optim.Adam(net.parameters(), lr=0.001)#优化器for epoch in range(5): # loop over the dataset multiple timesrunning_loss = 0.0for step, data in enumerate(train_loader, start=0):# get the inputs; data is a list of [inputs, labels]inputs, labels = data# zero the parameter gradientsoptimizer.zero_grad()#将历史损失梯度清零# forward + backward + optimizeoutputs = net(inputs)loss = loss_function(outputs, labels)loss.backward()#反向传播optimizer.step()# print statisticsrunning_loss += loss.item()if step % 500 == 499: # print every 500 mini-batcheswith torch.no_grad():#接下来计算过程中不计算损失梯度，更好分配内存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 = 0.0print('Finished Training')save_path = './Lenet.pth'torch.save(net.state_dict(), save_path)if __name__ == '__main__':main()
片
import torch
import torchvision.transforms as transforms
from PIL import Imagefrom model import LeNetdef 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('cat.jpg')im = Image.open('airplane.png').convert('RGB') # 转换为RGB图像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].numpy()predict = predict.item() # 从数组中提取标量值print(classes[int(predict)])if __name__ == '__main__':main()测试结果
