I cannot find main_cfg and I couldn't find where this should be used since in Colab demo there is this code snippet
matcher = LoFTR(config=default_cfg) if image_type == 'indoor': matcher.load_state_dict(torch.load("weights/indoor_ds.ckpt")['state_dict']) elif image_type == 'outdoor': matcher.load_state_dict(torch.load("weights/outdoor_ds.ckpt")['state_dict']) else: raise ValueError("Wrong image_type is given.") matcher = matcher.eval().cuda()
Even if I would use main_cfg, I would still get the same problem with key that is not recognized. How to solve this?
I cannot find main_cfg and I couldn't find where this should be used since in Colab demo there is this code snippet
matcher = LoFTR(config=default_cfg) if image_type == 'indoor': matcher.load_state_dict(torch.load("weights/indoor_ds.ckpt")['state_dict']) elif image_type == 'outdoor': matcher.load_state_dict(torch.load("weights/outdoor_ds.ckpt")['state_dict']) else: raise ValueError("Wrong image_type is given.") matcher = matcher.eval().cuda()
Even if I would use main_cfg, I would still get the same problem with key that is not recognized. How to solve this?