def set_num_points(self, pts): self.num_points = pts self.actual_number_of_points = pts def randomize(self): self.actual_number_of_points = min( max( np.random.randint(self.num_points * 0.8, self.num_points * 1.2), 1), self.points.shape[1], ) if __name__ == "__main__": from torchvision import transforms import data_utils as d_utils transforms = transforms.Compose([ d_utils.PointcloudToTensor(), d_utils.PointcloudRotate(axis=np.array([1, 0, 0])), d_utils.PointcloudScale(), d_utils.PointcloudTranslate(), d_utils.PointcloudJitter(), ]) dset = ModelNet40Cls(16, "./", train=True, transforms=transforms) print(dset[0][0]) print(dset[0][1]) print(len(dset)) dloader = torch.utils.data.DataLoader(dset, batch_size=32, shuffle=True)
def set_num_points(self, pts): self.num_points = pts self.actual_number_of_points = pts def randomize(self): self.actual_number_of_points = min( max( np.random.randint(self.num_points * 0.8, self.num_points * 1.2), 1 ), self.points.shape[1] ) if __name__ == "__main__": from torchvision import transforms import data_utils as d_utils transforms = transforms.Compose([ d_utils.PointcloudToTensor(), d_utils.PointcloudRotate(x_axis=True), d_utils.PointcloudScale(), d_utils.PointcloudTranslate(), d_utils.PointcloudJitter() ]) dset = ModelNet40Cls(16, "./", train=True, transforms=transforms) print(dset[0][0]) print(dset[0][1]) print(len(dset)) dloader = torch.utils.data.DataLoader(dset, batch_size=32, shuffle=True)