问题描述
我正在对音乐类型进行分类。 我用我的模型(即神经网络)构建了文件.h5。 现在我要使用它。 这是预测音乐类型的代码:
#%%
import librosa
import tensorflow as tf
import numpy as np
from collections import Counter
SAVED_MODEL_PATH = "modelLast.h5"
SAMPLES_TO_CONSIDER = 22050
DURATION = 30
SAMPLE_PER_TRACK = SAMPLES_TO_CONSIDER * DURATION
#%%
class _Keyword_Spotting_Service:
"""Singleton class for keyword spotting inference with trained models.
:param model: Trained model
"""
model = None
_mapping = [
"blues","classical","country","disco","hiphop","jazz","Metal","pop","reggae","rock"
]
_instance = None
def predict(self,file_path,num_mfcc=13,n_fft=2048,hop_length=512):
"""Extract MFCCs from audio file.
:param file_path (str): Path of audio file
:param num_mfcc (int): # of coefficients to extract
:param n_fft (int): Interval we consider to apply STFT. Measured in # of samples
:param hop_length (int): Sliding window for STFT. Measured in # of samples
:return MFCCs (ndarray): 2-dim array with MFCC data of shape (# time steps,# coefficients)
"""
num_segments = 10
num_samples_per_segment = int(SAMPLE_PER_TRACK / num_segments) # num of segments
# load audio file
signal,sample_rate = librosa.load(file_path)
# a faire
predicted_indexes = [0] * num_segments
predicted_mfcc = [0] * num_segments
for s in range(num_segments):
start_sample = num_samples_per_segment * s # s=0 -> 0
finish_sample = start_sample + num_samples_per_segment # s=0 -> num_samples_per_segment
mfcc = librosa.feature.mfcc(signal[start_sample:finish_sample],sample_rate,n_fft=n_fft,n_mfcc=num_mfcc,hop_length=hop_length)
MFCCs = mfcc.T
MFCCs = MFCCs[np.newaxis,...,np.newaxis]
# get the predicted label
predictions = self.model.predict(MFCCs)
print ("\nPredictions: {}".format(predictions))
predicted_indexes [s] = np.argmax(predictions)
predicted_mfcc [s] = np.max(predictions)
print("\nIndex list: {}".format(predicted_indexes))
print("\nIndex list Mfccs : {}".format(predicted_mfcc))
#predicted_index = np.bincount(predicted_indexes).argmax() # Méthode pour avoir l'index qui se répète le plus de fois
# Ajout de précision du code :
"""
Nous ressort de la liste les indexs qui se répètent le plus de fois et s'il y a plusieurs doublons
triplés,compare la valeurs des indexs et choisi l'index à la valeur la plus élevée
Voir le code python Liste.py pour plus de précision
"""
indices = list(map(lambda x: x[0],Counter(predicted_indexes).most_common()))
counts = list(map(lambda x: x[1],Counter(predicted_indexes).most_common()))
print("\nIndices présents dans la liste : ",indices)
print("\nNombre d'apparition des indices : ",counts)
max_indices = [indices[i] for i,x in enumerate(counts) if x == max(counts)]
result_mcfccs = []
for idx,id in enumerate(predicted_indexes):
if id in max_indices:
result_mcfccs.append(predicted_mfcc[idx])
result = max(result_mcfccs)
print("\n Indice se répétant le plus : ",max_indices)
print("\nValeur maximale de l'indice se répétant le plus : ",result)
indice = predicted_mfcc.index(result)
print("\nEmplacement de la valeur dans la lsite :",indice)
F= predicted_indexes.pop(indice)
print("\nRésultat final : ",F)
predicted_keyword = self._mapping[F]
return predicted_keyword
def Keyword_Spotting_Service():
"""Factory function for Keyword_Spotting_Service class.
:return _Keyword_Spotting_Service._instance (_Keyword_Spotting_Service):
"""
# ensure an instance is created only the first time the factory function is called
if _Keyword_Spotting_Service._instance is None:
_Keyword_Spotting_Service._instance = _Keyword_Spotting_Service()
_Keyword_Spotting_Service.model = tf.keras.models.load_model(SAVED_MODEL_PATH)
return _Keyword_Spotting_Service._instance
if __name__ == "__main__":
# create 2 instances of the keyword spotting service
kss = Keyword_Spotting_Service()
kss1 = Keyword_Spotting_Service()
# check that different instances of the keyword spotting service point back to the same object (singleton)
assert kss is kss1
# make a prediction
keyword = kss.predict("discoTrain.wav") # disco
#keyword = kss.predict("TheRiversGoingWildCUT.mp3") # Blues
#keyword = kss.predict("QuantumJazz.mp3") # Jazz
#keyword = kss.predict("QuantumJazzCUT.mp3") # Jazz
#keyword = kss.predict("AbsconseResilience.mp3") # Metal
#keyword = kss.predict("Nature.wav")
#keyword = kss.predict("elvis-presley-jailhouse-rock-music-video.mp3") # Rock
#keyword = kss.predict("bob-marley-no-woman-no-cry-official-video.mp3") # Reggae
#keyword = kss.predict("alan-jackson-chattahoochee-official-music-videoCUT.mp3") # Country
print(keyword)
File "C:\ProgramData\Anaconda3\envs\PMI\lib\site-packages\tensorflow_core\python\keras\utils\generic_utils.py",line 165,in class_and_config_for_serialized_keras_object
raise ValueError('UnkNown ' + printable_module_name + ': ' + class_name)
ValueError: UnkNown regularizer: L2
我该如何解决?
解决方法
我终于找到了为什么出现此错误。 它来自我的路径变量。 从互联网下载文件夹后,只需在路径变量中添加“ ffmpeg”即可。 这是链接:https://ffmpeg.org/download.html 我将文件夹直接复制到我的“ C”盘中,并将路径添加到路径变量中。
祝你好运!