Question

参考此链接：https://aqibsaeed.github.io/2016-09-03-urban-sound-classification-part-1/，我试图制作相同的waveplot数字，但是，我通过.py运行代码，有错误：

(tensorflow) yyydeMacBook-Pro:~ yyy$ python /Users/yyy/Desktop/1.py 
Traceback (most recent call last):
  File "/Users/yyy/Desktop/1.py", line 82, in <module>
    plot_waves(sound_names,raw_sounds)
  File "/Users/yyy/Desktop/1.py", line 42, in plot_waves
    librosa.display.waveplot(np.array(f),sr=22050)
AttributeError: 'module' object has no attribute 'display'

Answer 1

从此github issue我读到现在需要{{1}}。

Answer 2

由于0.6.0版本librosa发生了变化，您将收到这些错误。我修复了http://aqibsaeed.github.io/2016-09-03-urban-sound-classification-part-1/中的所有问题并使其适用于Python 3，librosa = 0.6.0

import glob
import os
import librosa
import librosa.display
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
from matplotlib.pyplot import specgram
%matplotlib inline

def load_sound_files(file_paths):
    raw_sounds = []
    for fp in file_paths:
        X,sr = librosa.load(fp)
        raw_sounds.append(X)
    return raw_sounds

def plot_waves(sound_names,raw_sounds):
    i = 1
    #fig = plt.figure(figsize=(25,60), dpi = 900)
    fig = plt.figure(figsize=(25,60))
    for n,f in zip(sound_names,raw_sounds):
        plt.subplot(10,1,i)
        librosa.display.waveplot(np.array(f),sr=22050)
        plt.title(n.title())
        i += 1
    plt.suptitle("Figure 1: Waveplot",x=0.5, y=0.915,fontsize=18)
    plt.show()

def plot_specgram(sound_names,raw_sounds):
    i = 1
    #fig = plt.figure(figsize=(25,60), dpi = 900)
    fig = plt.figure(figsize=(25,60))
    for n,f in zip(sound_names,raw_sounds):
        plt.subplot(10,1,i)
        specgram(np.array(f), Fs=22050)
        plt.title(n.title())
        i += 1
    plt.suptitle("Figure 2: Spectrogram",x=0.5, y=0.915,fontsize=18)
    plt.show()

def plot_log_power_specgram(sound_names,raw_sounds):
    i = 1
    #fig = plt.figure(figsize=(25,60), dpi = 900)
    fig = plt.figure(figsize=(25,60))
    for n,f in zip(sound_names,raw_sounds):
        plt.subplot(10,1,i)
        #D = librosa.logamplitude(np.abs(librosa.stft(f))**2, ref_power=np.max)
        D = librosa.core.amplitude_to_db(np.abs(librosa.stft(f))**2, ref=np.max)
        librosa.display.specshow(D,x_axis='time' ,y_axis='log')
        plt.title(n.title())
        i += 1
    plt.suptitle("Figure 3: Log power spectrogram",x=0.5, y=0.915,fontsize=18)
    plt.show()


sound_file_paths = ["57320-0-0-7.wav","24074-1-0-3.wav","15564-2-0-1.wav","31323-3-0-1.wav",
"46669-4-0-35.wav","89948-5-0-0.wav","40722-8-0-4.wav",
"103074-7-3-2.wav","106905-8-0-0.wav","108041-9-0-4.wav"]

sound_names = ["air conditioner","car horn","children playing",
"dog bark","drilling","engine idling", "gun shot",
"jackhammer","siren","street music"]

raw_sounds = load_sound_files(sound_file_paths)

plot_waves(sound_names,raw_sounds)
plot_specgram(sound_names,raw_sounds)
plot_log_power_specgram(sound_names,raw_sounds)

Answer 3

仅导入显示

import librosa.display
plt.figure(figsize=(12, 4))
librosa.display.waveplot(data, sr=sampling_rate)

output of the code

Answer 4

import os
import numpy as np
%pylab inline
import glob
import librosa.display
import matplotlib.pyplot as plt
import tensorflow as tf
plt.figure(figsize=(12,4))
librosa.display.waveplot(data,sr=sampling_rate)

librosa.display.waveplot（np.array（f），sr = 22050）----- AttributeError：'module'对象没有属性'display'

4 个答案: