我只是从这里使用此源代码
[链接] https://github.com/jaron/deep-listening/blob/master/3-us8k-cnn-extract-train.ipynb
它是有关特征提取的代码。我有pyhon 3.5,librosa(0.4.3),numpy(1.14.4)。我组合了librosa和numpy的多个版本,但是它总是会出现相同的错误
saving fold1
Traceback (most recent call last):
File "C:/Users/puppy/Desktop/test/test.py", line 72, in <module>
save_folds(save_dir)
File "C:/Users/puppy/Desktop/test/test.py", line 50, in save_folds
features, labels = extract_features(parent_dir, [fold_name])
File "C:/Users/puppy/Desktop/test/test.py", line 23, in extract_features
if (len(sound_clip[start:end]) == int(window_size)):
TypeError: slice indices must be integers or None or have an __index__ method
Process finished with exit code 1