合集请看：pyTorch入门合集
参考视频：https://www.bilibili.com/video/BV1hE411t7RN/?spm_id_from=333.337.search-card.all.click

利用已经训练好的模型，然后给它提供输入

照一张相关图片然后传入模型，查看结果是否复合预期

import torchvision  
from PIL import Image  
from model import *  

image_path = "../imgs/dog.png"  
image = Image.open(image_path)  
image = image.convert('RGB')  

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

image = transform(image)  

pan = torch.load("pan_method1.pth")  

image = torch.reshape(image, (1, 3, 32, 32))  
pan.eval()  
with torch.no_grad():  
    output = pan(image)  
print(output.argmax(1))

其实就是加载训练好的模型到实际使用场景中，看能否成功