PD-MeshNet
PD-MeshNet copied to clipboard
MIT-SPARK
Primal-Dual Mesh Convolutional Neural Networks
Hi, I was wondering if this implementation works out of the box for non-manifold meshes. Could you please let me know if it works for non-manifold meshes? Also, if it...
Are there any other options？ I am looking forward to hearing from you。
it seems that there is a issue when you launch for the first time a training jobs. In base_training_job.py line 203 you check if the checkpoint subfolder exists and if...
## Introduction Issue #6 comes from the bug that statement `os.path.exists(complete_path_logs_current_training_job)` always be `True`. When we start a new training job, this code https://github.com/MIT-SPARK/PD-MeshNet/blob/e3f6c01ceff260778daf5fea66125413309e4399/pd_mesh_net/utils/base_training_job.py#L202 ``` # Create the checkpoint subfolder...
I am training your UNet mesh segmenter model by running ```training_job_example_aliens_unet.py``` file and I get this error when I am trying to initialize the model. Is there a fix for...
torch.nn.modules.module.ModuleAttributeError: 'GATConvNoSelfLoops' object has no attribute 'weight'
I am running ```training_job_example_aliens_superpix.py``` and I am getting the above attribute error during forward() in model file
Hello, I hope you are well and safe. How can I prepare another data set (not CUBES or SHREC11) to run on your model (e.g: ModelNet40)? Are the meshes prior...
Hi, I am trying to do an edge contraction by training a segmentation model and during inference extracting the output from the pooling layer. However, the output is in a...
Hi, I've trained a model with your code in cubes dataset and saved checkpoints every 10 epoches. However, when I test on these checkpoints using test_job_1.py , the output accuracy...
