Question

以下代码使用音频文件在tensorflow：

中创建要素矩阵

import tensorflow as tf

directory = "audio_dataset/*.wav"

filenames = tf.train.match_filenames_once(directory)

init = (tf.global_variables_initializer(), tf.local_variables_initializer())

count_num_files = tf.size(filenames)
filename_queue = tf.train.string_input_producer(filenames)
reader = tf.WholeFileReader()
filename, file_contents = reader.read(filename_queue)

with tf.Session() as sess:
    sess.run(init)
    num_files = sess.run(count_num_files)

    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)

    for i in range(num_files):
        audio_file = sess.run(filename)
        print(audio_file)

这是一个将音频从时域转换到频域的工具包：

from bregman.suite import *


chromo = tf.placeholder(tf.float32)
max_freqs = tf.argmax(chromo, 0)


def get_next_chromogram(sess):
    audio_file = sess.run(filename)
    F = Chromagram(audio_file, nfft=16384, wfft=8192, nhop=2205)
    return F.X


def extract_feature_vector(sess, chromo_data):
    num_features, num_samples = np.shape(chromo_data)
    freq_vals = sess.run(max_freqs, feed_dict={chromo: chromo_data})
    hist, bins = np.histogram(freq_vals, bins=range(num_features + 1))
    return hist.astype(float) / num_samples


def get_dataset(sess):
    num_files = sess.run(count_num_files)
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)
    xs = []
    for _ in range(num_files):
        chromo_data = get_next_chromogram(sess)
        x = [extract_feature_vector(sess, chromo_data)]
        x = np.matrix(x)
        if len(xs) == 0:
            xs = x
        else:
            xs = np.vstack((xs, x))
    return xs

这会将数据聚集在两个质心周围：

k = 2
max_iterations = 100

def initial_cluster_centroids(X, k):
    return X[0:k, :]

def assign_cluster(X, centroids):
    expanded_vectors = tf.expand_dims(X, 0)
    expanded_centroids = tf.expand_dims(centroids, 1)
    distances = tf.reduce_sum(tf.square(tf.subtract(expanded_vectors, expanded_centroids)), 2)
    mins = tf.argmin(distances, 0)
    return mins

def recompute_centroids(X, Y):
    sums = tf.unsorted_segment_sum(X, Y, k)
    counts = tf.unsorted_segment_sum(tf.ones_like(X), Y, k)
    return sums / counts

with tf.Session() as sess:
    sess.run(init)
    X = get_dataset(sess)
    centroids = initial_cluster_centroids(X, k)
    i, converged = 0, False
    while not converged and i < max_iterations:
        i += 1
        Y = assign_cluster(X, centroids)
        centroids = sess.run(recompute_centroids(X, Y))
    print(centroids)

但我得到以下追溯：

Traceback (most recent call last):
  File "components.py", line 776, in <module>
    X = get_dataset(sess)
  File "ccomponents.py", line 745, in get_dataset
    chromo_data = get_next_chromogram(sess)
  File "coffee_components.py", line 728, in get_next_chromogram
    F = Chromagram(audio_file, nfft=16384, wfft=8192, nhop=2205)
  File "/Volumes/Dados/Documents/Education/Programming/Machine Learning/Manning/book/BregmanToolkit-master/bregman/features.py", line 143, in __init__
    Features.__init__(self, arg, feature_params)
  File "/Volumes/Dados/Documents/Education/Programming/Machine Learning/Manning/book/BregmanToolkit-master/bregman/features_base.py", line 70, in __init__
    self.extract()
  File "/Volumes/Dados/Documents/Education/Programming/Machine Learning/Manning/book/BregmanToolkit-master/bregman/features_base.py", line 213, in extract
    self.extract_funs.get(f, self._extract_error)()
  File "/Volumes/Dados/Documents/Education/Programming/Machine Learning/Manning/book/BregmanToolkit-master/bregman/features_base.py", line 711, in _chroma
    if not self._cqft():
  File "/Volumes/Dados/Documents/Education/Programming/Machine Learning/Manning/book/BregmanToolkit-master/bregman/features_base.py", line 588, in _cqft
    self._make_log_freq_map()
  File "/Volumes/Dados/Documents/Education/Programming/Machine Learning/Manning/book/BregmanToolkit-master/bregman/features_base.py", line 353, in _make_log_freq_map
    mxnorm = P.empty(self._cqtN) # Normalization coefficients        
TypeError: 'float' object cannot be interpreted as an index

据我所知，range是int而不是float。

有人可以在这里指出错误吗？

Answer 1

问题在于您使用的是Python 3，但Bregman Toolkit是用Python 2编写的。错误来自this line：

mxnorm = P.empty(self._cqtN)

self._cqtN是float。在Python 2中，pylab库接受浮点数作为输入：

pylab.empty(5.0)
__main__:1: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
array([ 0.,  0.,  0.,  0.,  0.])

但是，在Python 3中，您会得到与您相同的错误：

pylab.empty(5.0)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: 'float' object cannot be interpreted as an integer

您应该能够通过编辑我上面链接的文件中的行并将其转换为int来修复此错误：

mxnorm = P.empty(int(self._cqtN))

但是，如果由于版本不兼容而导致其他任何错误，我会感到惊讶。您可能想尝试使用Python 2或寻找Bregman Toolkit的替代方案。

Answer 2

您需要在第353行和第357页的feature_base.py

中将castself._cqtN更改为int

有 mxnorm = P.empty(int(self._cqtN))

和 for i in P.arange(int(self._cqtN))])

Python TypeError：＆＃39; float＆＃39;对象不能被解释为索引

2 个答案: