本文整理汇总了Python中vggish_postprocess.Postprocessor方法的典型用法代码示例。如果您正苦于以下问题：Python vggish_postprocess.Postprocessor方法的具体用法？Python vggish_postprocess.Postprocessor怎么用？Python vggish_postprocess.Postprocessor使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类vggish_postprocess的用法示例。
在下文中一共展示了vggish_postprocess.Postprocessor方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: import vggish_postprocess [as 别名]
# 或者: from vggish_postprocess import Postprocessor [as 别名]
def __init__(self, checkpoint, pca_params, input_tensor_name, output_tensor_name):
"""Create a new Graph and a new Session for every VGGishExtractor object."""
super(VGGishExtractor, self).__init__()
self.graph = tf.Graph()
with self.graph.as_default():
vggish_slim.define_vggish_slim(training=False)
sess_config = tf.ConfigProto(allow_soft_placement=True)
sess_config.gpu_options.allow_growth = True
self.sess = tf.Session(graph=self.graph, config=sess_config)
vggish_slim.load_defined_vggish_slim_checkpoint(self.sess, checkpoint)
# use the self.sess to init others
self.input_tensor = self.graph.get_tensor_by_name(input_tensor_name)
self.output_tensor = self.graph.get_tensor_by_name(output_tensor_name)
# postprocessor
self.postprocess = vggish_postprocess.Postprocessor(pca_params) 示例2: extract_audioset_embedding
# 需要导入模块: import vggish_postprocess [as 别名]
# 或者: from vggish_postprocess import Postprocessor [as 别名]
def extract_audioset_embedding():
"""Extract log mel spectrogram features.
"""
# Arguments & parameters
mel_bins = vggish_params.NUM_BANDS
sample_rate = vggish_params.SAMPLE_RATE
input_len = vggish_params.NUM_FRAMES
embedding_size = vggish_params.EMBEDDING_SIZE
'''You may modify the EXAMPLE_HOP_SECONDS in vggish_params.py to change the
hop size. '''
# Paths
audio_path = 'appendixes/01.wav'
checkpoint_path = os.path.join('vggish_model.ckpt')
pcm_params_path = os.path.join('vggish_pca_params.npz')
if not os.path.isfile(checkpoint_path):
raise Exception('Please download vggish_model.ckpt from '
'https://storage.googleapis.com/audioset/vggish_model.ckpt '
'and put it in the root of this codebase. ')
if not os.path.isfile(pcm_params_path):
raise Exception('Please download pcm_params_path from '
'https://storage.googleapis.com/audioset/vggish_pca_params.npz '
'and put it in the root of this codebase. ')
# Load model
sess = tf.Session()
vggish_slim.define_vggish_slim(training=False)
vggish_slim.load_vggish_slim_checkpoint(sess, checkpoint_path)
features_tensor = sess.graph.get_tensor_by_name(vggish_params.INPUT_TENSOR_NAME)
embedding_tensor = sess.graph.get_tensor_by_name(vggish_params.OUTPUT_TENSOR_NAME)
pproc = vggish_postprocess.Postprocessor(pcm_params_path)
# Read audio
(audio, _) = read_audio(audio_path, target_fs=sample_rate)
# Extract log mel feature
logmel = vggish_input.waveform_to_examples(audio, sample_rate)
# Extract embedding feature
[embedding_batch] = sess.run([embedding_tensor], feed_dict={features_tensor: logmel})
# PCA
postprocessed_batch = pproc.postprocess(embedding_batch)
print('Audio length: {}'.format(len(audio)))
print('Log mel shape: {}'.format(logmel.shape))
print('Embedding feature shape: {}'.format(postprocessed_batch.shape))