ValueError: a must be greater than 0

[xuan20050301]

(sound_separation) PS C:\Users\28231\Desktop\Wave-U-Net-master> python training.py
WARNING - Waveunet Training - No observers have been added to this run
INFO - Waveunet Training - Running command 'run'
INFO - Waveunet Training - Started
SCRIPT START
EPOCH: 0
Preparing MUSDB dataset! This could take a while...
C:\Users\28231\miniconda3\envs\sound_separation\lib\site-packages\musdb_init_.py:86: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
self.setup = yaml.load(f)
ERROR - Waveunet Training - Failed after 0:00:00!
Traceback (most recent calls WITHOUT Sacred internals):
File "training.py", line 162, in run
sup_model_path, sup_loss = optimise()
File "training.py", line 137, in optimise
model_path = train(load_model=model_path)
File "training.py", line 39, in train
dataset = Datasets.get_dataset(model_config, sep_input_shape, sep_output_shape, partition="train")
File "C:\Users\28231\Desktop\Wave-U-Net-master\Datasets.py", line 140, in get_dataset
val_idx = np.random.choice(len(dsd_train), size=25, replace=False)
File "mtrand.pyx", line 1120, in mtrand.RandomState.choice
ValueError: a must be greater than 0