Problem precomputing S3DIS Area_5_hallway_6

[tejaskhot]

In the precompute step, on running python tc.py experiments/stanford/dhnrgb/config.json --precompute, I get:

:: precompute
processing scan: Area_5_hallway_6, rot: 0
Traceback (most recent call last):
  File "tc.py", line 21, in <module>
    run_precompute(config)
  File "util/precompute.py", line 93, in run_precompute
    labels_gt=np.reshape(np.asarray(pcd_labels_down.point_cloud.colors)[:, 0], (num_points)),
  File "/usr0/home/tkhot/anaconda3/envs/tensorflow/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 257, in reshape
    return _wrapfunc(a, 'reshape', newshape, order=order)
  File "/usr0/home/tkhot/anaconda3/envs/tensorflow/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 52, in _wrapfunc
    return getattr(obj, method)(*args, **kwds)
ValueError: cannot reshape array of size 0 into shape (46214,)

Here, pcd_labels_down.point_cloud.colors is empty although in the preceding step before downsampling, pcd_labels.colors is correctly sized.

[syncle]

Not quite sure based on the provided log file. Just quick answer: can you check Area_5_hallway_6 is correctly downloaded?

[tejaskhot]

I tried downloading the data zip file again and ran into the same issue. The colors data is present until the down sampling step but is empty as the result of the downsampling. This happens for: Area_5_office_20 and Area_5_hallway_6.

[tatarchm]

The problem was in the 'get_data.py' script. The two scans you've mentioned have bad points which were not present in the output .pcd files but were present in the .labels files. This caused a shape mismatch. I fixed this now, you can re-run the 'get_data.py' script.

[tejaskhot]

That fixed it. Thanks!