rubenwiersma / hsn Goto Github PK
View Code? Open in Web Editor NEWCode for SIGGRAPH paper CNNs on Surfaces using Rotation-Equivariant Features
License: MIT License
Code for SIGGRAPH paper CNNs on Surfaces using Rotation-Equivariant Features
License: MIT License
Hi,
Thanks for the great contribution and for sharing the code.
I'm using HSN for segmentation (I'm using my own dataset). I had this error while doing preprocessing:
File "/hsn/datasets/shape_seg2.py", line 76, in process
data = self.pre_transform(data)
File "/path/site-packages/torch_geometric/transforms/compose.py", line 14, in __call__
data = t(data)
File "/hsn/transforms/multiscale_radius_graph.py", line 93, in __call__
pool_neigh = torch.from_numpy(vh.nearest(pos_vh, face_vh, idx_vh, labels_vh)).round().long().clamp(0, pool_idx.size(0) - 1).view(-1)
RuntimeError: checkFinite() failure: Non-finite matrix entry [2441,2441] = -nan
It's an error related to vector_heat
, do have an idea why this happening, and how can I solve it?
Thank you in advance!
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!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.