假設我們有以下維度的表格：
print(metadata.shape)-(8732, 8)
假設我們要讀取每一行的 slice_file_name （然后從驅動器讀取聲音檔案）并提取梅爾頻率：
def feature_extractor(file_name):
audio,sample_rate =librosa.load(file_name,res_type='kaiser_fast')
mfccs_features =librosa.feature.mfcc(y=audio,sr=sample_rate,n_mfcc=40)
mfccs_scaled_features =np.mean(mfccs_features.T,axis=0)
return mfccs_scaled_features
如果我使用以下回圈：
from tqdm import tqdm
extracted_features =[]
for index_num, row in tqdm(metadata.iterrows()):
file_name = os.path.join(os.path.abspath(Base_Directory),str(row["slice_file_name"]))
final_class_labels=row["class"]
data=feature_extractor(file_name)
extracted_features.append([data,final_class_labels])
它總共需要以下時間：
3555it [21:15, 2.79it/s]/usr/local/lib/python3.7/dist-packages/librosa/core/spectrum.py:224: UserWarning: n_fft=2048 is too small for input signal of length=1323
n_fft, y.shape[-1]
8326it [48:40, 3.47it/s]/usr/local/lib/python3.7/dist-packages/librosa/core/spectrum.py:224: UserWarning: n_fft=2048 is too small for input signal of length=1103
n_fft, y.shape[-1]
8329it [48:41, 3.89it/s]/usr/local/lib/python3.7/dist-packages/librosa/core/spectrum.py:224: UserWarning: n_fft=2048 is too small for input signal of length=1523
n_fft, y.shape[-1]
8732it [50:53, 2.86it/s]
我怎樣才能優化這段代碼以在更短的時間內完成這件事？有可能的？
uj5u.com熱心網友回復：
您可以嘗試并行運行特征提取器，這可能會在您的資料框中使用mfccs_scaled_features.
from pandarallel import pandarallel
pandarallel.initialize()
PATH = os.path.abspath(Base_Directory)
def feature_extractor(file_name):
# If using windows, you may need to put these here~
# import librosa
# import numpy as np
# import os
file_name = os.path.join(PATH, file_name)
audio,sample_rate = librosa.load(file_name, res_type='kaiser_fast')
mfccs_features = librosa.feature.mfcc(y=audio, sr=sample_rate, n_mfcc=40)
mfccs_scaled_features = np.mean(mfccs_features.T, axis=0)
return mfccs_scaled_features
df['mfccs_scaled_features'] = df['slice_file_name'].parallel_apply(feature_extractor)
轉載請註明出處，本文鏈接：https://www.uj5u.com/qianduan/472480.html