xinge008/Cylinder3D

Mismatch in shape when running the demo

Opened this issue · 4 comments

WEIJIARONG99 commented

python demo_folder.py --demo-folder model_load_dir --save-folder results
demo_folder.py --demo-folder model_load_dir --save-folder results
Namespace(config_path='config/semantickitti.yaml', demo_folder='model_load_dir', demo_label_folder='', save_folder='results')
[480 360 32]
matched parameter sets: 226, and no matched: 48
Traceback (most recent call last):
File "demo_folder.py", line 151, in
main(args)
File "demo_folder.py", line 103, in main
demo_dataset_loader):
File "/home/weijiarong/anaconda3/envs/master_thesis/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 530, in next
data = self._next_data()
File "/home/weijiarong/anaconda3/envs/master_thesis/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1224, in _next_data
return self._process_data(data)
File "/home/weijiarong/anaconda3/envs/master_thesis/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1250, in _process_data
data.reraise()
File "/home/weijiarong/anaconda3/envs/master_thesis/lib/python3.7/site-packages/torch/_utils.py", line 457, in reraise
raise exception
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/weijiarong/anaconda3/envs/master_thesis/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/home/weijiarong/anaconda3/envs/master_thesis/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/weijiarong/anaconda3/envs/master_thesis/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/weijiarong/Desktop/Cylinder3D/dataloader/dataset_semantickitti.py", line 192, in getitem
data = self.point_cloud_dataset[index]
File "/home/weijiarong/Desktop/Cylinder3D/dataloader/pc_dataset.py", line 50, in getitem
raw_data = np.fromfile(self.im_idx[index], dtype=np.float32).reshape((-1, 4))
ValueError: cannot reshape array of size 55885386 into shape (4)

Anyone met the similar error?

ZixuanChen613 commented

I met the same error... waiting for an answer

ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/opt/conda/envs/4dplsca/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/opt/conda/envs/4dplsca/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/opt/conda/envs/4dplsca/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/workspace/code/Cylinder3D/dataloader/dataset_semantickitti.py", line 192, in getitem
data = self.point_cloud_dataset[index]
File "/workspace/code/Cylinder3D/dataloader/pc_dataset.py", line 52, in getitem
raw_data = np.fromfile(self.im_idx[index], dtype=np.float32).reshape((-1, 4))
ValueError: cannot reshape array of size 293 into shape (4)

WEIJIARONG99 commented
ZhouYC-X commented

I encountered similar problem and solved it by "python demo_folder.py --demo-folder /mnt/data/datasets/kitti/sequences/00/velodyne/ --save-folder ./results/". Good luck.

christophTUM commented

Does anyone else still has this problem?