python-3.x - 在这种情况下看门狗的 on_created 的事件参数是什么？

Question

我希望我的看门狗类中的 on_created 方法返回一个值。但是，我不知道 on_created 函数的事件参数是什么，所以我可以调用它。

这是我的看门狗类和 on_created 函数

class FrameHandler(FileSystemEventHandler):

    def on_created(self, event): # when file is created
        # Produce evaluation for the frame

        device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") 
        
        path = '/home/Desktop/mask-detector-model.pt'
        model_ft = models.mobilenet_v2(pretrained=True)
        model_ft.classifier[1] = torch.nn.Linear(in_features=model_ft.classifier[1].in_features, out_features=3)
        model_ft.load_state_dict(torch.load(path, map_location = device))

        class_names = ['MASKED', 'NOT_MASKED', 'NO_PERSON']

        image_transforms = transforms.Compose([
                 transforms.Resize(256),
                  transforms.CenterCrop(224),
                  transforms.ToTensor(),
                  transforms.Normalize([0.5237], [0.2611]) ])


        data_dir = '/home/Desktop/Frames'
        test_dataset = datasets.ImageFolder(root=data_dir, transform= image_transforms)
        test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=True, num_workers=1, pin_memory=True)
        with torch.no_grad(): 
            for i, (inputs, labels) in enumerate(test_loader):
                outputs = model_ft(inputs)
                _, preds = torch.max(outputs, 1)

                
                for j in range(inputs.size()[0]):
                     prediction = class_names[preds[j]]
                     
               
        return prediction    

标签： python-3.xoopeventspython-watchdog