search

mehta-lab / microDL

3D virtual staining with 2D and 2.5D U-Nets
BSD 3-Clause "New" or "Revised" License
27 stars 7 forks source link

Training error without augmentation #215

Closed Soorya19Pradeep closed 1 year ago

Soorya19Pradeep commented 1 year ago

The following error appears when augmentations are removed from config file for training 2.5D model.

File "/home/soorya.pradeep/microDL/micro_dl/training/training.py", line 146, in generate_dataloaders
    torch_data_container = ds.TorchDatasetContainer(
  File "/home/soorya.pradeep/microDL/micro_dl/input/dataset.py", line 75, in __init__
    ) = gp_utils.multi_zarr_source(
  File "/home/soorya.pradeep/microDL/micro_dl/utils/gunpowder_utils.py", line 287, in multi_zarr_source
    train_idx = int(len(all_sources) * data_split["train"])
TypeError: int() argument must be a string, a bytes-like object or a number, not 'list'
ziw-liu commented 1 year ago

This problem is specific to gunpowder. Closing in favor of #220.