dschwertfeger

def ConvModel(n_classes, sample_rate=16000, duration=4,
              fft_size=_FFT_SIZE, hop_size=_HOP_SIZE, n_mels=_N_MEL_BINS):
    n_samples = sample_rate * duration
    
    # Accept raw audio data as input
    x = Input(shape=(n_samples,), name='input', dtype='float32')
    # Process into log-mel-spectrograms. (This is your custom layer!)
    y = LogMelSpectrogram(sample_rate, fft_size, hop_size, n_mels)(x)
    # Normalize data (on frequency axis)
    y = BatchNormalization(axis=2)(y)

dschwertfeger

def power_to_db(S, amin=1e-16, top_db=80.0):
    """Convert a power-spectrogram (magnitude squared) to decibel (dB) units.

    Computes the scaling ``10 * log10(S / max(S))`` in a numerically
    stable way.

    Based on:
    https://librosa.github.io/librosa/generated/librosa.core.power_to_db.html
    """
    def _tf_log10(x):

dschwertfeger

class LogMelSpectrogram(tf.keras.layers.Layer):
    """Compute log-magnitude mel-scaled spectrograms."""

    def __init__(self, sample_rate, fft_size, hop_size, n_mels,
                 f_min=0.0, f_max=None, **kwargs):
        super(LogMelSpectrogram, self).__init__(**kwargs)
        self.sample_rate = sample_rate
        self.fft_size = fft_size
        self.hop_size = hop_size
        self.n_mels = n_mels

dschwertfeger

import argparse
import math
import os
from multiprocessing import Pool, cpu_count

import numpy as np
import pandas as pd
import tensorflow as tf
from tqdm import tqdm

dschwertfeger

import os
import tensorflow as tf

AUTOTUNE = tf.data.experimental.AUTOTUNE


def _parse_batch(record_batch, sample_rate, duration):
    n_samples = sample_rate * duration

    # Create a description of the features

dschwertfeger

import tensorflow as tf


def _bytestring_feature(list_of_bytestrings):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=list_of_bytestrings))


def _int_feature(list_of_ints):  # int64
    return tf.train.Feature(int64_list=tf.train.Int64List(value=list_of_ints))

dschwertfeger

import pandas as pd
import tensorflow as tf

AUTOTUNE = tf.data.experimental.AUTOTUNE


def get_dataset(df):
    file_path_ds = tf.data.Dataset.from_tensor_slices(df.file_path)
    label_ds = tf.data.Dataset.from_tensor_slices(df.label)
    return tf.data.Dataset.zip((file_path_ds, label_ds))

dschwertfeger

import argparse
import math
import os

import numpy as np
import pandas as pd
import tensorflow as tf


_BASE_DIR = os.path.dirname(os.path.abspath(__file__))