isl-org / isl-org/Open3D-ML

No such file or directory: './Kitti/bboxes.pkl'

Open
#484 2 comments 0 reactions 0 assignees View on GitHub
bug
Dominant language
Python
Stars
2.3k
Forks
365
Avg merge
4h 6m
Merged PRs (30d)
1

Description

### Checklist

- [X] I have searched for [similar issues](https://github.com/isl-org/Open3D-ML/issues).
- [X] I have tested with the [latest development wheel](http://www.open3d.org/docs/latest/getting_started.html#development-version-pip).
- [X] I have checked the [release documentation](http://www.open3d.org/docs/release/) and the [latest documentation](http://www.open3d.org/docs/latest/) (for `master` branch).

### Describe the issue

I was trying to train PointPillar with Kitti.
I used the default script for downloading kitti and then I run this script:

But I get the following error:

### Steps to reproduce the bug

```python
`python scripts/run_pipeline.py torch -c ml3d/configs/pointpillars_kitti.yml --split train --dataset.dataset_path ./Kitti --pipeline ObjectDetection --dataset.use_cache True
`
```

### Error message

`INFO - 2022-03-01 14:15:44,665 - object_detection - DEVICE : cuda
INFO - 2022-03-01 14:15:44,665 - object_detection - Logging in file : ./logs/PointPillars_KITTI_torch/log_train_2022-03-01_14:15:44.txt
INFO - 2022-03-01 14:15:44,665 - kitti - Found 3712 pointclouds for training
preprocess: 0%| | 0/3712 [00:00
main()
File "scripts/run_pipeline.py", line 153, in main
pipeline.run_train()
File "/home/bilel/anaconda3/envs/cell_tower/lib/python3.6/site-packages/open3d/_ml3d/torch/pipelines/object_detection.py", line 278, in run_train
'steps_per_epoch_train', None))
File "/home/bilel/anaconda3/envs/cell_tower/lib/python3.6/site-packages/open3d/_ml3d/torch/dataloaders/torch_dataloader.py", line 62, in __init__
self.cache_convert(name, data, attr)
File "/home/bilel/anaconda3/envs/cell_tower/lib/python3.6/site-packages/open3d/_ml3d/utils/dataset_helper.py", line 56, in __call__
output = self.func(*data)
File "/home/bilel/anaconda3/envs/cell_tower/lib/python3.6/site-packages/open3d/_ml3d/torch/models/point_pillars.py", line 232, in preprocess
data = self.augmenter.augment(data, attr, seed=rng)
File "/home/bilel/anaconda3/envs/cell_tower/lib/python3.6/site-packages/open3d/_ml3d/datasets/augment/augmentation.py", line 572, in augment
self.load_gt_database(**cfg['ObjectSample'])
File "/home/bilel/anaconda3/envs/cell_tower/lib/python3.6/site-packages/open3d/_ml3d/datasets/augment/augmentation.py", line 506, in load_gt_database
db_boxes = pickle.load(open(pickle_path, 'rb'))
FileNotFoundError: [Errno 2] No such file or directory: '/media/bilel/Data/Datasets/Kitti/bboxes.pkl`

### Expected behavior

The training should work as expected in the documentation

### Open3D, Python and System information

```markdown
- Operating system: Ubuntu 20.04
- Python version: 3.6.13 |Anaconda, Inc.| (default, Jun 4 2021, 14:25:59)
[GCC 7.5.0]
(e.g. Python 3.8 / output from `import sys print(sys.version)`)
- Open3D version: 0.14.1 (output from python: `print(open3d.__version__)`)
- System type: arm64 (x84 / arm64 / apple-silicon / jetson / rpi)
- Is this remote workstation?: no yes or no
- How did you install Open3D?: pip (e.g. pip, conda, build from source)
- Compiler version (if built from source): (e.g. gcc 7.5, clang 7.0)
```

### Additional information

_No response_

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.