MeshCNN
MeshCNN copied to clipboard
Convolutional Neural Network for 3D meshes in PyTorch
I find the serial numbers does not match the serial number of original coseg meshes? Can you provide the corresponding relationship by xml or json? Thank you very much!
Traceback (most recent call last): File "train.py", line 30, in model.optimize_parameters() File "/home/ch/MeshCNN-master/models/mesh_classifier.py", line 66, in optimize_parameters out = self.forward() File "/home/ch/MeshCNN-master/models/mesh_classifier.py", line 57, in forward out = self.net(self.edge_features, self.mesh)...
Hi, During training I am getting the below error. > ``` meshcnn) C:\ml_work\MeshCNN>python train.py --dataroot datasets/mydataset --name mydataset --ncf 64 128 256 256 --pool_res 600 450 300 180 --norm group...
Hello Rana, Thanks for this repository, very helpful. I'd like to use your code in order to train a model on non-watertight models. However, I'm getting stuck on this error....
Traceback (most recent call last): File "train.py", line 30, in model.optimize_parameters() File "/home/ch/MeshCNN-master/models/mesh_classifier.py", line 66, in optimize_parameters out = self.forward() File "/home/ch/MeshCNN-master/models/mesh_classifier.py", line 57, in forward out = self.net(self.edge_features, self.mesh)...
Dear Ms Hanocka! I'm trying to apply your model into my project, but when I created the dataset myself, I found that *.eseg and *.seseg are really hard to find...
Hi, your project is really interesting :-D I've read your project's readme and followed the basic steps. Then I got a question, How to take untrained mesh data as input...
This is what is stated in wiki. > Each mesh is simplified to roughly the same number of edges, then new ground-truth segmentation files for the low resolution meshes (eseg)...
@ranahanocka @emepetres @bertjiazheng : I found a link in the wiki, any update on this https://github.com/ranahanocka/MeshCNN/wiki/Segmentation ? I want to tag parts and train my own 3D segmentation model ?
I read all the code, but not yet understand how soft_labels work in MeshCNN, and how can i create my own dataset with soft_labels