How to use Custom (or albumentation) augmentations on Detectron 2?

I have the below code where I'm using default augmentation during training of Detectron 2 but the problem is that there are very few augmentations that are useful to me.

1. Here is something like what I to achieve with my own functions.

2. This github issue link tries to solve.

Want to whether it is the right way to do it and also, how could I Look at the augmented image result if I want to see what's happening?

import detectron2.data.transforms as T
from detectron2.data import detection_utils as utils

def custom_mapper(dataset_dict):
    
    dataset_dict = copy.deepcopy(dataset_dict)
    image = utils.read_image(dataset_dict["file_name"], format="BGR")
    transform_list = [T.RandomBrightness(0.8, 1.2),
                      T.RandomContrast(0.8, 1.2),
                      T.RandomSaturation(0.8, 1.2),
                      ]
    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"] = utils.filter_empty_instances(instances)
    return dataset_dict

But the problem is that

1. I want to build my custom augmentation or use albumentations for the purpose.
2. I don't want to use all of the augmentations every time and there's no probability in the above transformations that I have used. So a way around would be to use something like OneOf on individual or a group.

from How to use Custom (or albumentation) augmentations on Detectron 2?