Problems while running notebook examples
Created by: pvnieo
Hi,
Thank you for the great contribution and for sharing the code.
I have two questions!
The first one is how long does this network take for training, for example for classification or segmentation?
The second one, is that, while trying to run the provided notebooks for classification and segmentation, I run into errors while creating the dataloaders. In the classification case using shrec dataset, I got the following error:
/content/transforms/normalize_area.py in __call__(self, data)
17 # Normalize by surface area
18 pos_vh, face_vh = data.pos.cpu().numpy(), data.face.cpu().numpy().T
---> 19 area = 1 / np.sqrt(vh.surface_area(pos_vh, face_vh))
20 data.pos = data.pos * area
21
RuntimeError: GC_SAFETY_ASSERT FAILURE from /tmp/pip-req-build-7f8xsuhg/deps/geometry-central/src/surface/halfedge_factories.cpp:18 - polygon list has index 5081 >= num vertices 252
and for the segmentation case, I got the following error:
/content/datasets/shape_seg.py in process(self)
131 seg_path = osp.join(mit_seg, filename.replace('.obj', '.eseg'))
132 segs = torch.from_numpy(np.loadtxt(seg_path)).long()
--> 133 data.y = edge_to_vertex_labels(data.face, segs, data.num_nodes)
134 if self.pre_filter is not None and not self.pre_filter(data):
135 continue
/content/utils/harmonic.py in edge_to_vertex_labels(faces, labels, n_nodes)
124 edge_index = torch.LongTensor(0, 2)
125 for face in faces.transpose(0, 1):
--> 126 edges = torch.stack([face[:2], face[1:], face[::2]], dim=0)
127 for idx, edge in enumerate(edges):
128 edge = edge.sort().values
RuntimeError: stack expects each tensor to be equal size, but got [1] at entry 0 and [0] at entry 1
Can please tell how to solve this problem, or provide a collab link to run the notebooks directly?
Thank you in advance!