ranahanocka / MeshCNN

Convolutional Neural Network for 3D meshes in PyTorch
MIT License
1.56k stars 314 forks source link

IndexError: index out of range #110

Open pvnieo opened 3 years ago

pvnieo commented 3 years ago

Hi,

I'm using MeshCNN for a segmentation task. I didn't change anything in the code, but I got the following error:

File "/meshcnn/models/networks.py", line 393, in forward
    fe, before_pool = conv((fe, meshes))
  File "/meshcnn/models/networks.py", line 226, in __call__
    return self.forward(x)
  File "/meshcnn/models/networks.py", line 246, in forward
    x2 = self.pool(x2, meshes)
  File "/meshcnn/models/layers/mesh_pool.py", line 21, in __call__
    return self.forward(fe, meshes)
  File "/meshcnn/models/layers/mesh_pool.py", line 34, in forward
    self.__pool_main(mesh_index)
  File "meshcnn/models/layers/mesh_pool.py", line 50, in __pool_main
    value, edge_id = heappop(queue)
IndexError: index out of range

What is the reson of this error?

Eisorak commented 3 years ago

Hi

have you thought of changing the variable input-edges? because you have to give the size of your meshes.

wlcosta commented 2 years ago

@pvnieo were you able to solve this issue? I am having the same problem.

pvnieo commented 2 years ago

Hi @wlcosta

Sorry, I don't remember I solved it, and I just saw the response of @Eisorak today :sweat_smile:

kajalsanklecha commented 5 days ago

How to change the --pool-res and --ncf to run it my dataset with 768 edges in every object? I am facing the same error. Please anyone who was able to solve this error, please respond!