Using my own obj files for training

[Sawaiz8]

I have been trying to use my own dataset with meshcnn but I am not able to identity how I can make your code to accept my dataset.
I created a new dataset in the dataset folder it has the same directory structure as the shrec16 dataset but when I run the code after changing the dataroot directory to datasets/anchor_obj in train.sh file, I get the following error:

File "/home/sawaiz/Documents/Lab/Projects/MeshCNN/MeshCNN-master/data/init.py", line 12, in CreateDataset
dataset = ClassificationData(opt)
File "/home/sawaiz/Documents/Lab/Projects/MeshCNN/MeshCNN-master/data/classification_data.py", line 19, in init
self.get_mean_std()
File "/home/sawaiz/Documents/Lab/Projects/MeshCNN/MeshCNN-master/data/base_dataset.py", line 32, in get_mean_std
for i, data in enumerate(self):
File "/home/sawaiz/Documents/Lab/Projects/MeshCNN/MeshCNN-master/data/classification_data.py", line 34, in getitem
edge_features = pad(edge_features, self.opt.ninput_edges)
File "/home/sawaiz/Documents/Lab/Projects/MeshCNN/MeshCNN-master/util/util.py", line 22, in pad
return np.pad(input_arr, pad_width=npad, mode='constant', constant_values=val)
File "/home/sawaiz/.local/lib/python3.10/site-packages/numpy/lib/arraypad.py", line 748, in pad
pad_width = _as_pairs(pad_width, array.ndim, as_index=True)
File "/home/sawaiz/.local/lib/python3.10/site-packages/numpy/lib/arraypad.py", line 518, in _as_pairs
raise ValueError("index can't contain negative values")
ValueError: index can't contain negative values

I feel I have to process my data in a certain way but I am not sure. Can you please clarify how I can do that?
My dataset is a face dataset. I used mediapipe facial landmarker to get the facial landmarks of a face in 3d and then convert the point cloud into a mesh using open3d library. I can access the obj files and see the objects. The number of vertices and faces are variable in all these files.

[yy030425]

Hi! I get the same error.And I processed my data,like simplifying to the same faces,but it still didn't work.Were you able to solve the issue?

[Sawaiz8]

Nope. I gave up