卷积神经网络测试代码-cifar10

import torch
import torchvision
from PIL import Image
from torch import nn


image_path = '../g.jpg'
image = Image.open(image_path)
print(image)

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

image = transform(image)


# 搭建神经网络
class li(nn.Module):
    def __init__(self):
        super(li, 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
Li=li()


model = torch.load(r'E:\python存储\pytorch\小土堆\li19.pth',map_location='cpu')
image=torch.reshape(image,(1,3,32,32))
# 如果有dropout就写，良好代码习惯
# model.eval()
with torch.no_grad():
    output=model(image)
print(output)
a=output.argmax(1)
print(output.argmax(1))
d=a.item()
c={0:'airplane',1:'mobile',2:'bird',3:'cat',4:'der',5:'dog',6:'frog',7:'horse',8:'shp',9:'truck'}
print(c[d])