Question on val_preds and snapshops in plot and test scripts

[StellaLulu]

Hi, I was running the script using Colab and encountered two error when running the plot and test script for S3DIS. After I read issue #89, it seems that I am missing both val_preds or snapshots in the log folder. Any advices would be appreciated.

python3 plot_convergence.py

Preparing ply files
Done in 0.0s
   mean   | ceiling    floor      wall      beam     column    window     door     chair     table    bookcase    sofa     board    clutter  
----------|----------------------------------------------------------------------------------------------------------------------------------
   8.3    |   22.8      40.9      14.1      8.3       0.9       1.3       0.0       0.4       0.3       8.3       8.3       0.3       1.8    
path: results/Log_2021-03-16_04-05-48
b'kernel_points'
b'parameters.txt'
b'training.txt'
b'val_IoUs.txt'
Traceback (most recent call last):
  File "plot_convergence.py", line 804, in <module>
    compare_convergences_segment(dataset, logs, logs_names)
  File "plot_convergence.py", line 547, in compare_convergences_segment
    snap_epochs, snap_IoUs = load_snap_clouds(path, dataset)
  File "plot_convergence.py", line 177, in load_snap_clouds
    cloud_folders = np.array([join(path, f) for f in listdir(path) if f.startswith('val_preds')])
  File "plot_convergence.py", line 177, in <listcomp>
    cloud_folders = np.array([join(path, f) for f in listdir(path) if f.startswith('val_preds')])
TypeError: startswith first arg must be bytes or a tuple of bytes, not str

python3 test_any_model.py

Creating Model
**************

Traceback (most recent call last):
  File "test_any_model.py", line 281, in <module>
    test_caller(chosen_log, chosen_snapshot, on_val)
  File "test_any_model.py", line 146, in test_caller
    snap_steps = [int(f[:-5].split('-')[-1]) for f in os.listdir(snap_path) if f[-5:] == '.meta']
FileNotFoundError: [Errno 2] No such file or directory: 'results/Log_2021-03-16_04-09-59/snapshots'