基于PyTorch与TensorRT的cifar10推理加速

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

上一篇:基于TensorRT优化的Machine Translation


下一篇:TensorRT加速原理记录