Pointnet_Pointnet2_pytorch
Pointnet_Pointnet2_pytorch copied to clipboard
For different number of classes?
Can it work for different number of classes? My class number = 2 Where I change in train_semseg.py? What is label_weights, the value of the similar to class number? Anyone help me please.
Yes it does work for arbitrary class numbers (though these must exist in your training data).
You need to change the final layers output size in the model definition.