rkakash59

@gihunsong Even I am facing the same issue.

@gihunsong you can try : `model = EfficientNet.from_name('efficientnet-b0', num_classes=5) model.load_state_dict(weights_path)`

@gihunsong that was a suggestion. I missed model.eval() during inference so l was getting inconsistent results. Now I am getting consistent results.

@slimbuck sorry I could not respond earlier. 1. Yes, between splat centers. 2. It is for indoor scene reconstruction using Gaussian splatting, then measuring length of walls and other general...

Can you suggest how to get .ply file from checkpoint file(if possible). I want to use other viewers as well which supports .ply format.