Xelawk

```python class get_model(nn.Module): def __init__(self, num_classes, normal_channel=False): super(get_model, self).__init__() ... self.sa1 = PointNetSetAbstractionMsg(512, [0.1, 0.2, 0.4], [32, 64, 128], 3+additional_channel, [[32, 32, 64], [64, 64, 128], [64, 96, 128]]) self.sa2...

What's the reason of this error

1

``` #training meshes = 1004 ---------- Network initialized ------------- [Network] Total number of parameters : 1.321 M ----------------------------------------------- Traceback (most recent call last): File "/Dev/xelawk_dev/MeshCNN/train.py", line 30, in model.optimize_parameters() File...

How to do data processing

1

How to use the manifold software as you recommended in wiki for manifolding the mesh, do you have any good suggestions? And for large meshes, is it better to manifold...

Zero problem on my private dataset

2

Here is the problem I encounterd when I was trying to training meshcnn with my private dataset. ``` arch: mconvnet batch_size: 16 beta1: 0.9 checkpoints_dir: ./checkpoints continue_train: False dataroot: datasets/shape59_simplify...

For citation about the program of nmf_sparse

2

Dear Dr. Hiroyuki Kasai I hope you are well. Recently I have been using your program nmf_sparse of NMFLibrary for doing some research, and it's very well for running, many...

我发现train.py，损失函数是Cross_entropy, 如果多Multi-labels的图像分类，不应该是使用Binary entropy吗？望解答！

for Nan or given missing value of 0.0f, how to correctly deal with it by xgboost of go version

？？？？？？？？？？

In my application scene, cordinate on the y-axis are most within a big range. How should i try to modify the source code to adjust my application.

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What happened? --disable-console-progressbars option was used to disable...