search

Sangminhong / ACL-SPC_PyTorch

Official implementation of the paper "ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion" (CVPR 2023)
34 stars 5 forks source link

Would you please share the SemanticKITTI dataset used in ACL-SPC ? #12

Closed MillyMaMa closed 7 months ago

MillyMaMa commented 7 months ago

Dear author @Sangminhong ： I plan to train ACL-SPC on SemanticKITTI dataset，I download it from SemanticKITTI website following the guidance in issue 2, but I find its formate is not .pkl while the code need .pkl to load SemanticKITTI .

class SemanKITTIDataset:
    def _load_dataset(self, split):
        self.data = []
        for sequence_id in self.split_map[split]:
            fname = osp.join(self.directory, '{:02d}.pkl'.format(sequence_id))
            with open(fname, 'rb') as f:
                instances = pickle.load(f)

Would you please share the SemanticKITTI dataset used in ACL-SPC with me? I have send emails to you for two times, please check them, appreciate for your time.

xingjinderhuoche commented 1 week ago

Have you solved it yet？