How to detect objects in tensor flow for specific objects in video for example only bottle

to detect objects in tensor flow for specific objects in the video for example bottle.

I have indices = np.argwhere(classes == 44)* where class 44 is for bottle and it is throwing an error :too many indices for array

and it is working fine for class 1 which is for persons. it is working fine
Can someone help me with this?

Visualization of the results of detection.

        boxes = np.squeeze(boxes)
        scores = np.squeeze(scores)
        classes = np.squeeze(classes)

        **indices = np.argwhere(classes == 44)**
        boxes = np.squeeze(boxes[indices])
        scores = np.squeeze(scores[indices])
        classes = np.squeeze(classes[indices])
        
        vis_util.visualize_boxes_and_labels_on_image_array(
            image_np,
            np.squeeze(boxes),
            np.squeeze(classes).astype(np.int32),
            np.squeeze(scores),
            category_index,
            use_normalized_coordinates=True,
            line_thickness=8)