Training model on non-native tags

[ScubaDiving]

Hi,

I'm trying to train BlendMask on a different dataset then the built-ins. It is a dataset of building facades. I converted the dataset to coco from labelme and placed it in the dataset folder in the following way:

coco\
    thing_train2017
        --all .npz files created from running prepare_thing_sem_from_instance,py
    annotations
        instances_train2017.json

I'm pretty sure the dataset I'm using is in the 2014 version but I don't think it matters (does it?)

When I run this command:

python tools/train_net.py --config-file .\configs\BlendMask\R_101_3x.yaml --num-gpus 1 OUTPUT_DIR training_dir/fcos_R_50_1x 

I basically get this error:

AssertionError: Attribute 'thing_classes' in the metadata of 'coco_2017_train' cannot be set to a different value!
['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', '
zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass'
, 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier',
 'toothbrush'] != ['building']

What am I doing wrong?
Would appreciate any help as I'm quite new to ML and such.

Thanks!