完整的模型验证套路

在网络上下载图片，然后使用训练好的模型进行测试，查看预测结果。
文中所有模型(test_1.pth)为前文保存的网络模型

import torch

import torchvision
from PIL import Image
from torch import nn

image_path = "dog.png"
image = Image.open(image_path)
print(image)

transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32, 32)), torchvision.transforms.ToTensor()])

class Test(nn.Module):
    def __init__(self):
        super(Test, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64*4*4, 64),
            nn.Linear(64, 10)
        )

    def forward(self, x):
        x = self.model(x)
        return x

#在cpu上使用GPU的训练模型时要指定训练模型
model = torch.load("test_1.pth", map_location=torch.device('cpu'))
image = torch.reshape(image, (1, 3, 32, 32))
model = eval()
with torch.no_grad():
    output = model(image)
print(output.argmax(1))