Can not get any meshes after training

[ChangeFWorld]

I haved trained the model using my pictures and womask.conf but can not get any result. A part of the output text:

[export.py:72 -          export_mesh() ] Exporting 0 faces as PLY
[exp_runner.py:342 -        validate_mesh() ] End

When validating meshes,there is always nothing to export . I don't know what happends The exported .ply files are also empty

[mch0dmin]

I haved trained the model using my pictures and womask.conf but can not get any result. A part of the output text:

[export.py:72 -          export_mesh() ] Exporting 0 faces as PLY
[exp_runner.py:342 -        validate_mesh() ] End

When validating meshes,there is always nothing to export . I don't know what happends The exported .ply files are also empty

hi @Lumine7 , I have encountered the same problem. Have you resolved it?

[ChangeFWorld]

I haved trained the model using my pictures and womask.conf but can not get any result. A part of the output text:

[export.py:72 -          export_mesh() ] Exporting 0 faces as PLY
[exp_runner.py:342 -        validate_mesh() ] End

When validating meshes,there is always nothing to export . I don't know what happends The exported .ply files are also empty

hi @Lumine7 , I have encountered the same problem. Have you resolved it?

@mch0dmin Well, that's a long time since then and I have forget most of the details. I remember it's probably because you didn't remove the noise from the periphery of the point cloud.

[mch0dmin]

hi @Lumine7 , thanks for your reply.

I used a DTU dataset and ran the following command,

python exp_runner.py --mode train --conf ./confs/wmask.conf --case dtu_scan105

After about 12 hours, the command execution ended, and the log is as follows,

...
iter:299700 loss = 0.060289688408374786 lr=2.5001220174518157e-05
100%|██████████████████████████████████████████████████████████████████████████████████████▉| 299799/300000 [11:57:34<00:27,  7.25it/s]./exp/dtu_scan105/wmask
iter:299800 loss = 0.049736443907022476 lr=2.5000544103200803e-05
100%|██████████████████████████████████████████████████████████████████████████████████████▉| 299899/300000 [11:57:48<00:13,  7.25it/s]./exp/dtu_scan105/wmask
iter:299900 loss = 0.06598859280347824 lr=2.5000137382696864e-05
100%|██████████████████████████████████████████████████████████████████████████████████████▉| 299999/300000 [11:58:01<00:00,  7.25it/s]./exp/dtu_scan105/wmask
iter:300000 loss = 0.061162158846855164 lr=2.5000000013467564e-05
Validate: iter: 300000, camera: 17
threshold: 0.0
[export.py:72 -          export_mesh() ] Exporting 11508 faces as PLY
[exp_runner.py:342 -        validate_mesh() ] End
100%|███████████████████████████████████████████████████████████████████████████████████████| 300000/300000 [11:58:15<00:00,  6.96it/s]

[export.py:72 - export_mesh() ] Exporting 11508 faces as PLY [exp_runner.py:342 - validate_mesh() ] End

Then i want to extract surface from trained model, and ran the following command,

$ python exp_runner.py --mode validate_mesh --conf ./confs/wmask.conf --case dtu_scan105 --is_continue 
Hello Wooden
Load data: Begin
Load data: End
Traceback (most recent call last):
  File "exp_runner.py", line 389, in <module>
    runner = Runner(args.conf, args.mode, args.case, args.is_continue)
  File "exp_runner.py", line 82, in __init__
    model_list_raw = os.listdir(os.path.join(self.base_exp_dir, 'checkpoints'))
FileNotFoundError: [Errno 2] No such file or directory: './exp/dtu_scan105/wmask/checkpoints'

As you can see, it reported an error and could not find ./exp/dtu_scan105/wmask/checkpoints.

[mch0dmin]

I have exchanged other datasets and it works fine. Thanks again.