input_dict['segmentation'] = annos["inmodal_seg"] KeyError: 'inmodal_seg'

[RickySumX]

epochs: 0%| | 0/80 [00:00<?, ?it/s] Traceback (most recent call last): File "train.py", line 202, in main() File "train.py", line 154, in main train_model( File "/202121622952/UPIDet/tools/train_utils/train_utils.py", line 111, in train_model accumulated_iter = train_one_epoch( File "/202121622952/UPIDet/tools/train_utils/train_utils.py", line 25, in train_one_epoch batch = next(dataloader_iter) File "/root/anaconda3/envs/upi/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 530, in next data = self._next_data() File "/root/anaconda3/envs/upi/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 570, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/root/anaconda3/envs/upi/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/root/anaconda3/envs/upi/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/202121622952/UPIDet/tools/../pcdet/datasets/kitti/kitti_dataset.py", line 407, in getitem input_dict['segmentation'] = annos["inmodal_seg"] KeyError: 'inmodal_seg'

I print（annos）,but i find annos isn't include 'inmodal_seg':

'name': array(['Car', 'DontCare', 'DontCare'], dtype='<U8'), 'truncated': array([ 0., -1., -1.]), 'occluded': array([ 0., -1., -1.]), 'alpha': array([ 1.92, -10. , -10. ]), 'bbox': array([[254.08, 184.29, 360.28, 232.81], [583.3 , 181.83, 593.3 , 191.83], [500.5 , 177.94, 520.2 , 190.52]], dtype=float32), 'dimensions': array([[ 4.33, 1.48, 1.97], [-1. , -1. , -1. ], [-1. , -1. , -1. ]]), 'location': array([[ -10.3 , 1.89, 24.82], [-1000. , -1000. , -1000. ], [-1000. , -1000. , -1000. ]], dtype=float32), 'rotation_y': array([ 1.53, -10. , -10. ]), 'score': array([-1., -1., -1.]), 'difficulty': array([ 0, -1, -1], dtype=int32), 'index': array([ 0, -1, -1], dtype=int32), 'gt_boxes_lidar': array([[25.10887909, 10.32051182, -0.85387194, 4.33 , 1.97 , 1.48 , -3.10079633]]), 'num_points_in_gt': array([163, -1, -1], dtype=int32)}

[Eaphan]

Please prepare KITTI Dataset as we suggested in the Readme file. "Please download them in this link and replace the original files."

[RickySumX]

Thanks for your help

[Bennyliiiiii]

@RickySumX I also encountered the same problem, have you solved it?