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?)
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:
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:
I basically get this error:
What am I doing wrong? Would appreciate any help as I'm quite new to ML and such.
Thanks!