eval_network.py error

[sarbjit-longia]

Using TensorFlow backend.
class_names = ['music_wav', 'speech_wav']
total files = 26 , going to load total_load = 0
total files = 26 , going to load total_load = 0
get_sample_dimensions: bagpipe.wav.npz: melgram.shape = (1, 96, 2584, 1)
melgram dimensions: (1, 96, 2584, 1)

Loading class 1/2: 'music_wav', File 1/13: Preproc/Test/music_wav/bagpipe.wav.npz Traceback (most recent call last):
File "eval_network.py", line 135, in
eval_network(weights_file=args.weights, classpath=args.classpath, batch_size=args.batch_size)
File "eval_network.py", line 63, in eval_network
X_test, Y_test, paths_test, class_names = build_dataset(path=classpath, batch_size=batch_size)
File "panotti\datautils.py", line 235, in build_dataset
X[load_count,:,:] = melgram
IndexError: index 0 is out of bounds for axis 0 with size 0