ARTS-S pytorch用c++实现推理

训练的代码,以cifar为例

# -*- coding: utf-8 -*-
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

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=2)

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=2)
classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
dataiter = iter(trainloader)
images, labels = dataiter.next()


class Net(torch.jit.ScriptModule):
    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)

    @torch.jit.script_method
    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


net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

for epoch in range(1):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if i % 2000 == 1999:
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0
        if i == 2:
            break
net.save("/Users/zhouyang3/CLionProjects/hello_world/a.pt")
print('Finished Training')

c++推理代码

#include <torch/script.h>
#include <typeinfo>
#include <iostream>
#include <memory>

int main(int argc, const char* argv[]) {
    if (argc != 2) {
        std::cerr << "usage: example-app <path-to-exported-script-module>\n";
        return -1;
    }

    // Deserialize the ScriptModule from a file using torch::jit::load().
    std::shared_ptr<torch::jit::script::Module> module = torch::jit::load(argv[1]);

    assert(module != nullptr);
    std::cout << "ok\n";
    std::vector<torch::jit::IValue> inputs;
    inputs.push_back(torch::ones({1, 3, 32, 32}));
    at::Tensor output = module->forward(inputs).toTensor();
    std::cout << "AAAAA" << '\n';
    std::cout << output.argmax() << '\n';
    std::cout << "BBBBB" << '\n';
}