PointNet系列代码复现详解(1)—PointNet分类部分_葭月甘九的博客-CSDN博客
PointNet系列代码复现详解(2)—PointNet++part_seg_葭月甘九的博客-CSDN博客
train_semseg.py
与前面代码基本一致,写法固定,就是对一些模型运行参数的设置以及训练流程的安排。
pointnet_sem_seg.py
class get_model(nn.Module):
def __init__(self, num_class):
super(get_model, self).__init__()
self.k = num_class
self.feat = PointNetEncoder(global_feat=False, feature_transform=True, channel=9)
self.conv1 = torch.nn.Conv1d(1088, 512, 1)
self.conv2 = torch.nn.Conv1d(5