How to pass batch of images to pre-trained model?

[Wilann]

I'm trying to figure out how to perform inference using a pre-trained model on a single image via "Run a pre-trained detectron2 model" in their CoLab Tutorial. But I can't figure out how to pass the model a batch of images.

My current code is below
Note: I'm unsure whether I have to use DefaultPredictor(...) or build_model(...)

class Frames_Dataset(Dataset):
    
    def __init__(self, frames):

        self.preprocess = transforms.Compose([
            transforms.ToPILImage(),
            transforms.Resize(512),
            transforms.ToTensor(),
            transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
        ])

        self.frames = frames

    def __getitem__(self, index):
        frame_preprocessed = self.preprocess(self.frames[index])
        frame_detectron2_format = [{'image': frame} for frame in frame_preprocessed]
        return frame_detectron2_format

    def __len__(self):
        return len(self.frames)

frames = ... # list of frames of shape (8393, 3, 512, 512)
frames_dataset = Frames_Dataset(frames)
frames_dataloader = DataLoader(frames_dataset, batch_size=100, shuffle=False, num_workers=4)

cfg = get_cfg()
config_name = "COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml"

cfg.merge_from_file(model_zoo.get_config_file(config_name))

cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.9

cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url(config_name)

predictor = DefaultPredictor(cfg)

model = build_model(cfg)
model.eval()

If anyone could point me in the right direction I'd be greatly appreciated!
Thank you for your time.