一、思路
注:整个项目目前还有些欠缺,但可行
1、基于PyTorch训练出cifar10模型
2、以ONNX(Open Neural Network Exchange)格式导出模型cifar10.onnx
3、下载cifar10二进制版本数据集
4、创建TensorRT(vs c++)项目,解析模型,进行推理
二、基于PyTorch的cifar10神经网络模型
import torch import torchvision import torchvision.transforms as transforms import matplotlib.pyplot as plt import numpy as np import torch.nn as nn import torch.nn.functional as F import torch.optim as optim import datetime device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") # Assuming that we are on a CUDA machine, this should print a CUDA device: print(device) class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(3, 6, 5) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(6, 16, 5) self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = x.view(-1, 16 * 5 * 5) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x # functions to show an image def imshow(img): img = img / 2 + 0.5 # unnormalize npimg = img.numpy() plt.imshow(np.transpose(npimg, (1, 2, 0))) plt.show() # load dataset transform = transforms.Compose( [transforms.ToTensor()]) # transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) 这里原始数据不做标准化处理 trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=0) testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform) testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=0) classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck') # get some random training images dataiter = iter(trainloader) images, labels = dataiter.next() # show images imshow(torchvision.utils.make_grid(images)) # print labels print(' '.join('%5s' % classes[labels[j]] for j in range(4))) net = Net() net = Net().to(device) criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) for epoch in range(2): running_loss = 0.0 for i, data in enumerate(trainloader, 0): # get the inputs; data is a list of [inputs, labels] # inputs, labels = data inputs, labels = data[0].to(device), data[1].to(device) # zero the parameter gradients optimizer.zero_grad() # forward + backward + optimize outputs = net(inputs) loss = criterion(outputs, labels) loss.backward() optimizer.step() # print statistics running_loss += loss.item() if i % 2000 == 1999: # print every 2000 mini-batches print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000)) running_loss = 0.0 print('Finished Training') correct = 0 total = 0 start = datetime.datetime.now() with torch.no_grad(): for data in trainloader: images, labels = data images, labels = images.to(device), labels.to(device) outputs = net(images) _, predicted = torch.max(outputs.data, 1) total += labels.size(0) correct += (predicted == labels).sum().item() print('Accuracy of the network on the 50000 test images: %d %%' % ( 100 * correct / total)) end = datetime.datetime.now() print((end - start).seconds, 's') # 导出onnx模型 dummy_input = torch.randn(1, 3, 32, 32, device='cuda') input_names = ['input'] output_names = ['output'] torch.onnx.export(net, dummy_input, "cifar10.onnx", verbose='True', input_names=input_names, output_names=output_names)
三、待续