Error on running on subset of Shapenet Dataset

[1995YogeshSharma]

Hi, I picked out two classes of Shapenet pre-processed data and placed it in a custom folder maintaining directory structure. I want to run the point cloud -> mesh generation on this network. But, when I run python generate.py configs/pointcloud/onet_pretrained.yaml I get following error

Any help is appreciated!

[rahulvenkk]

I faced the same issue. It turns out that in im2mesh/core.py, lines 90-93

self.models += [
                {'category': c, 'model': m}
                for m in models_c 
            ]

models_c sometimes contains the empty string ''. This cause the dataloader to fail towards the end. Changing it to this made it work.

self.models += [
                {'category': c, 'model': m}
                for m in models_c if m!=''
            ]