ML-KWS-for-MCU:input_data.py

class AudioProcessor(object):
  """Handles loading, partitioning, and preparing audio training data."""

  def __init__(self, data_url, data_dir, silence_percentage, unknown_percentage,
               wanted_words, validation_percentage, testing_percentage,
               model_settings):
    self.data_dir = data_dir
    self.maybe_download_and_extract_dataset(data_url, data_dir)
    self.prepare_data_index(silence_percentage, unknown_percentage,
                            wanted_words, validation_percentage,
                            testing_percentage)
    self.prepare_background_data()
    self.prepare_processing_graph(model_settings)

data_url:指向datasets链接地址

data_dir:指向datasets存储位置

silence_percentage:假如训练时期望识别的Words在datasets中的总个数是100个，当silence_percentage=10的话，就表示给训练的集合中添加10个静音元素。

unknown_percentage:假如训练时期望识别的Words在datasets中的总个数是100个，当unknown_percentage=10的话，就表示给训练的集合中添加10个未知元素。

PS:所以参与训练的集合元素按照数据性质分为三类:静音+未知+期望words。

wanted_words:期望识别的Word

PS:参与训练的集合元素按照训练流程分为三类training、validation、testing。

validation_percentage:validation占了多少。

testing_percentage:testing占了多少。

model_settings:

---

  def maybe_download_and_extract_dataset(self, data_url, dest_directory):
    """Download and extract data set tar file.

根据data_url下载datasets，data_dir表示下载到某个地方。

如果本地已有datasets，可以在在给脚本的参数里写'--data_url='，data_dir指向datasets所在位置。

---

  def prepare_data_index(self, silence_percentage, unknown_percentage,
                         wanted_words, validation_percentage,
                         testing_percentage):
    """Prepares a list of the samples organized by set and label.

该函数主要目的是获得三个参数:self.data_index、self.words_list、self.word_to_index。

1.self.data_index

self.data_index = {'validation': [], 'testing': [], 'training': []}

元素:{'label': word, 'file': wav_path}

	silence	unknown	wanted words...
training
validation
testing

    # Look through all the subfolders to find audio samples
    search_path = os.path.join(self.data_dir, '*', '*.wav')
    for wav_path in gfile.Glob(search_path):
      _, word = os.path.split(os.path.dirname(wav_path))
      word = word.lower()
      # Treat the '_background_noise_' folder as a special case, since we expect
      # it to contain long audio samples we mix in to improve training.
      if word == BACKGROUND_NOISE_DIR_NAME:
        continue
      all_words[word] = True
      set_index = which_set(wav_path, validation_percentage, testing_percentage)
      # If it's a known class, store its detail, otherwise add it to the list
      # we'll use to train the unknown label.
      if word in wanted_words_index:
        self.data_index[set_index].append({'label': word, 'file': wav_path})
      else:
        unknown_index[set_index].append({'label': word, 'file': wav_path})

    # We need an arbitrary file to load as the input for the silence samples.
    # It's multiplied by zero later, so the content doesn't matter.
    silence_wav_path = self.data_index['training'][0]['file']
    for set_index in ['validation', 'testing', 'training']:
      set_size = len(self.data_index[set_index])
      silence_size = int(math.ceil(set_size * silence_percentage / 100))
      for _ in range(silence_size):
        self.data_index[set_index].append({
            'label': SILENCE_LABEL,
            'file': silence_wav_path
        })
      # Pick some unknowns to add to each partition of the data set.
      random.shuffle(unknown_index[set_index])
      unknown_size = int(math.ceil(set_size * unknown_percentage / 100))
      self.data_index[set_index].extend(unknown_index[set_index][:unknown_size])

    # Make sure the ordering is random.
    for set_index in ['validation', 'testing', 'training']:
      random.shuffle(self.data_index[set_index])

2.self.words_list

self.words_list = prepare_words_list(wanted_words)

3.self.word_to_index

    self.word_to_index = {}
    for word in all_words:
      if word in wanted_words_index:
        self.word_to_index[word] = wanted_words_index[word]
      else:
        self.word_to_index[word] = UNKNOWN_WORD_INDEX
    self.word_to_index[SILENCE_LABEL] = SILENCE_INDEX

---