ZLIB error when training

[cgalau97]

Hi everyone,

I'm getting this error: zlib.error: Error -3 while decompressing data: invalid distance code while running next command !nnUNetv2_train Dataset111_SEL 2d 0 --npz. The images and labels I am using are in NRRD format. Could that be a problem? Moreover, I'm using Windows and my data is in an external SSD. I'm using CUDA (NVIDIA GeForce RTX 3050 Ti Laptop GPU)

Do you have any clue of what I may try to solve it?

Here the full log of the error:

"""
Traceback (most recent call last):
  File "C:\Users\cgalau\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\pool.py", line 125, in worker
    result = (True, func(*args, **kwds))
                    ^^^^^^^^^^^^^^^^^^^
  File "C:\Users\cgalau\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\pool.py", line 51, in starmapstar
    return list(itertools.starmap(args[0], args[1]))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\nnunetv2\training\dataloading\utils.py", line 15, in _convert_to_npy
    np.save(npz_file[:-3] + "npy", a['data'])
                                   ~^^^^^^^^
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\numpy\lib\npyio.py", line 253, in __getitem__
    return format.read_array(bytes,
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\numpy\lib\format.py", line 823, in read_array
    data = _read_bytes(fp, read_size, "array data")
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\numpy\lib\format.py", line 958, in _read_bytes
    r = fp.read(size - len(data))
        ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\cgalau\AppData\Local\Programs\Python\Python311\Lib\zipfile.py", line 951, in read
    data = self._read1(n)
           ^^^^^^^^^^^^^^
  File "C:\Users\cgalau\AppData\Local\Programs\Python\Python311\Lib\zipfile.py", line 1027, in _read1
    data = self._decompressor.decompress(data, n)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
zlib.error: Error -3 while decompressing data: invalid distance code
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "c:\Users\cgalau\Desktop\UOC\TFM\venv\Scripts\nnUNetv2_train.exe\__main__.py", line 7, in <module>
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\nnunetv2\run\run_training.py", line 268, in run_training_entry
    run_training(args.dataset_name_or_id, args.configuration, args.fold, args.tr, args.p, args.pretrained_weights,
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\nnunetv2\run\run_training.py", line 204, in run_training
    nnunet_trainer.run_training()
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\nnunetv2\training\nnUNetTrainer\nnUNetTrainer.py", line 1234, in run_training
    self.on_train_start()
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\nnunetv2\training\nnUNetTrainer\nnUNetTrainer.py", line 806, in on_train_start
    unpack_dataset(self.preprocessed_dataset_folder, unpack_segmentation=True, overwrite_existing=False,
  File "C:\Users\cgalau\Desktop\UOC\TFM\venv\Lib\site-packages\nnunetv2\training\dataloading\utils.py", line 33, in unpack_dataset
    p.starmap(_convert_to_npy, zip(npz_files,
  File "C:\Users\cgalau\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\pool.py", line 375, in starmap
    return self._map_async(func, iterable, starmapstar, chunksize).get()
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\cgalau\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\pool.py", line 774, in get
    raise self._value
zlib.error: Error -3 while decompressing data: invalid distance code

Thanks for your help!
Cristian