Problems with using my own data set

[1ysine]

Hi,I converted my data set to wireframe format and encountered the following error.I have converted the json format to hdf5 format with offset, line_level, df,but an error is reported. I don't know why.

Traceback (most recent call last):
File "/root/miniconda3/envs/deeplsd/lib/python3.9/runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/root/miniconda3/envs/deeplsd/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/root/lys/DeepLSD/deeplsd/scripts/train.py", line 252, in
training(conf, output_dir, args)
File "/root/lys/DeepLSD/deeplsd/scripts/train.py", line 116, in training
train_loader = dataset.get_data_loader('train')
File "/root/lys/DeepLSD/deeplsd/datasets/wireframe_ha.py", line 99, in get_data_loader
return DataLoader(self.get_dataset(split), batch_size=batch_size,
File "/root/miniconda3/envs/deeplsd/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 376, in init
sampler = RandomSampler(dataset, generator=generator) # type: ignore[arg-type]
File "/root/miniconda3/envs/deeplsd/lib/python3.9/site-packages/torch/utils/data/sampler.py", line 164, in init
raise ValueError(
ValueError: num_samples should be a positive integer value, but got num_samples=0

[rpautrat]

Did you make sure that the path to your dataset was correct and that your custom dataset was properly initialized? Because if it doesn't find any sample, it probably means that it couldn't find any training image...

[1ysine]

Did you make sure that the path to your dataset was correct and that your custom dataset was properly initialized? Because if it doesn't find any sample, it probably means that it couldn't find any training image...

I got these outputs
[02/13/2025 16:29:33 INFO] Creating dataset WireframeHA
[02/13/2025 16:29:33 INFO] Found 103 in image folder.
[02/13/2025 16:29:33 INFO] Found 103 in GT folder.

[Truring]

@rpautrat Could you help me with this issue? Thank you very much! #52