Closed Steve-Tod closed 5 years ago
Hi, I read your paper and your code and I got one question. Why do you use conv2D instead of linear to implement mlp? Like here: https://github.com/charlesq34/pointnet/blob/d64d2398e55b24f69e95ecb549ff7d4581ffc21e/models/pointnet_cls.py#L44
@Steve-Tod It's simply a convenient way to do the weight-sharing of the MLPs (across number of samples)
I got it, Thanks.
Hi, I read your paper and your code and I got one question. Why do you use conv2D instead of linear to implement mlp? Like here: https://github.com/charlesq34/pointnet/blob/d64d2398e55b24f69e95ecb549ff7d4581ffc21e/models/pointnet_cls.py#L44