I want to add the normalize term in augmentation transform

Here is my mapper for augmentation

def mapper2(dataset_dict):
    dataset_dict = copy.deepcopy(dataset_dict)  # it will be modified by code below
    #image = utils.read_image(dataset_dict["file_name"], format="BGR")    
    image = utils.read_image(dataset_dict["file_name"], format="RGB")    

    transform_list = [
                   
                    T.RandomFlip(prob=0.5, horizontal=False, vertical=True)
                    ,T.ResizeShortestEdge(short_edge_length=(640, 672, 704, 736, 768, 800), max_size=1333, sample_style='choice')
                    #,T.RandomCrop('relative_range', (0.4, 0.6))
                    #,T.GridSampleTransform()
 
                    
                      ]
    image, transforms = T.apply_transform_gens(transform_list, image)
    dataset_dict["image"] = torch.as_tensor(image.transpose(2, 0, 1).astype("float32"))

  
    annos = [
        utils.transform_instance_annotations(obj, transforms, image.shape[:2])
        for obj in dataset_dict.pop("annotations")
        if obj.get("iscrowd", 0) == 0
    ]

    instances = utils.annotations_to_instances(annos, image.shape[:2])
    dataset_dict["instances"] = instances
    return dataset_dict

I want to put normalize option like T.GridSampleTransform()
but when I perform the above code

TypeError: __init__() missing 2 required positional arguments: 'grid' and 'interp'

GridSampleTransform doesn’t seem to be a built-in transformation and based on the raised error message it requires two input arguments: grid and interp, so you would have to provide them.
Since I cannot find the implementation, I can just guess that the arguments might be similar to the grid_sample method.