使用 VGGish_train_demo.py(下面的完整脚本),我们如何返回我们的模型,以便它可以再次用于新数据,例如使用model.fit(features)
model = this_model()
在类似的脚本中,我通常会在模型定义和结尾处看到类似return model
的内容。但是,我不知道如何整合像第一行这样的东西?
脚本。Github repo在这里,查看main(_)
函数
from __future__ import print_function
from random import shuffle
import numpy as np
import tensorflow.compat.v1 as tf
import tf_slim as slim
import vggish_input
import vggish_params
import vggish_slim
flags = tf.app.flags
flags.DEFINE_integer(
'num_batches', 30,
'Number of batches of examples to feed into the model. Each batch is of '
'variable size and contains shuffled examples of each class of audio.')
flags.DEFINE_boolean(
'train_vggish', True,
'If True, allow VGGish parameters to change during training, thus '
'fine-tuning VGGish. If False, VGGish parameters are fixed, thus using '
'VGGish as a fixed feature extractor.')
flags.DEFINE_string(
'checkpoint', 'vggish_model.ckpt',
'Path to the VGGish checkpoint file.')
FLAGS = flags.FLAGS
_NUM_CLASSES = 3
def _get_examples_batch():
"""Returns a shuffled batch of examples of all audio classes.
Note that this is just a toy function because this is a simple demo intended
to illustrate how the training code might work.
Returns:
a tuple (features, labels) where features is a NumPy array of shape
[batch_size, num_frames, num_bands] where the batch_size is variable and
each row is a log mel spectrogram patch of shape [num_frames, num_bands]
suitable for feeding VGGish, while labels is a NumPy array of shape
[batch_size, num_classes] where each row is a multi-hot label vector that
provides the labels for corresponding rows in features.
"""
# Make a waveform for each class.
num_seconds = 5
sr = 44100 # Sampling rate.
t = np.arange(0, num_seconds, 1 / sr) # Time axis
# Random sine wave.
freq = np.random.uniform(100, 1000)
sine = np.sin(2 * np.pi * freq * t)
# Random constant signal.
magnitude = np.random.uniform(-1, 1)
const = magnitude * t
# White noise.
noise = np.random.normal(-1, 1, size=t.shape)
# Make examples of each signal and corresponding labels.
# Sine is class index 0, Const class index 1, Noise class index 2.
sine_examples = vggish_input.waveform_to_examples(sine, sr)
sine_labels = np.array([[1, 0, 0]] * sine_examples.shape[0])
const_examples = vggish_input.waveform_to_examples(const, sr)
const_labels = np.array([[0, 1, 0]] * const_examples.shape[0])
noise_examples = vggish_input.waveform_to_examples(noise, sr)
noise_labels = np.array([[0, 0, 1]] * noise_examples.shape[0])
# Shuffle (example, label) pairs across all classes.
all_examples = np.concatenate((sine_examples, const_examples, noise_examples))
all_labels = np.concatenate((sine_labels, const_labels, noise_labels))
labeled_examples = list(zip(all_examples, all_labels))
shuffle(labeled_examples)
# Separate and return the features and labels.
features = [example for (example, _) in labeled_examples]
labels = [label for (_, label) in labeled_examples]
return (features, labels)
def main(_):
with tf.Graph().as_default(), tf.Session() as sess:
# Define VGGish.
embeddings = vggish_slim.define_vggish_slim(training=FLAGS.train_vggish)
# Define a shallow classification model and associated training ops on top
# of VGGish.
with tf.variable_scope('mymodel'):
# Add a fully connected layer with 100 units. Add an activation function
# to the embeddings since they are pre-activation.
num_units = 100
fc = slim.fully_connected(tf.nn.relu(embeddings), num_units)
# Add a classifier layer at the end, consisting of parallel logistic
# classifiers, one per class. This allows for multi-class tasks.
logits = slim.fully_connected(
fc, _NUM_CLASSES, activation_fn=None, scope='logits')
tf.sigmoid(logits, name='prediction')
# Add training ops.
with tf.variable_scope('train'):
global_step = tf.train.create_global_step()
# Labels are assumed to be fed as a batch multi-hot vectors, with
# a 1 in the position of each positive class label, and 0 elsewhere.
labels_input = tf.placeholder(
tf.float32, shape=(None, _NUM_CLASSES), name='labels')
# Cross-entropy label loss.
xent = tf.nn.sigmoid_cross_entropy_with_logits(
logits=logits, labels=labels_input, name='xent')
loss = tf.reduce_mean(xent, name='loss_op')
tf.summary.scalar('loss', loss)
# We use the same optimizer and hyperparameters as used to train VGGish.
optimizer = tf.train.AdamOptimizer(
learning_rate=vggish_params.LEARNING_RATE,
epsilon=vggish_params.ADAM_EPSILON)
train_op = optimizer.minimize(loss, global_step=global_step)
# Initialize all variables in the model, and then load the pre-trained
# VGGish checkpoint.
sess.run(tf.global_variables_initializer())
vggish_slim.load_vggish_slim_checkpoint(sess, FLAGS.checkpoint)
# The training loop.
features_input = sess.graph.get_tensor_by_name(
vggish_params.INPUT_TENSOR_NAME)
for _ in range(FLAGS.num_batches):
(features, labels) = _get_examples_batch()
[num_steps, loss_value, _] = sess.run(
[global_step, loss, train_op],
feed_dict={features_input: features, labels_input: labels})
print('Step %d: loss %g' % (num_steps, loss_value))
if __name__ == '__main__':
tf.app.run()