如何在 TensorFlow 中对多个类进行分类

Question

我已经关注了 youtube 上的一个教程，该教程向我展示了如何对 2 个数据集进行分类（咳嗽，不是咳嗽），但现在我需要添加一个额外的类，即打喷嚏，因此需要训练 3 个类（咳嗽，打喷嚏，其他），我不知道该怎么做。请帮忙！！！

在代码中，模型在 2 个类别（咳嗽、not_cough）上进行训练并且表现相当不错，但我无法让它在多个类别（例如（咳嗽、打喷嚏、其他））上工作。

import os
from matplotlib import pyplot as plt
import tensorflow as tf 
import tensorflow_io as tfio
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.layers import Conv2D, Dense, Flatten, MaxPool2D, Dropout,TimeDistributed, Reshape
from tensorflow.keras.optimizers.legacy import Adam
from keras import layers
from keras.utils import to_categorical

def load_wav_16k_mono(filename):
    # Load encoded wav file
    file_contents = tf.io.read_file(filename)
    # Decode wav (tensors by channels) 
    wav, sample_rate = tf.audio.decode_wav(file_contents, desired_channels=1)
    # Removes trailing axis
    wav = tf.squeeze(wav, axis=-1)
    sample_rate = tf.cast(sample_rate, dtype=tf.int64)
    # Goes from 44100Hz to 16000hz - amplitude of the audio signal
    wav = tfio.audio.resample(wav, rate_in=sample_rate, rate_out=16000)
    return wav

def preprocess(file_path, label): 
    wav = load_wav_16k_mono(file_path)
    wav = wav[:8000]
    zero_padding = tf.zeros([8000] - tf.shape(wav), dtype=tf.float32)
    wav = tf.concat([zero_padding, wav],0)
    
    spectrogram = tf.signal.stft(wav, frame_length=100, frame_step=20)
    spectrogram = tf.abs(spectrogram)
    spectrogram = tf.expand_dims(spectrogram, axis=2)
    return spectrogram, label


def get_CNN(input_shape):
    model = Sequential()
    model.add(Conv2D(16, (3,3), activation='relu', input_shape=input_shape))
    model.add(Conv2D(16, (3,3), activation='relu'))
    model.add(MaxPool2D((2,2)))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dense(1, activation='softmax'))
    
    model.compile('Adam', loss='BinaryCrossentropy', metrics=[tf.keras.metrics.Recall(),tf.keras.metrics.Precision(),'accuracy'])
    model.summary() # drop in some max pool layers to reduce params
    return model
    

def main():
    POS_COUGH = "./data/cough"
    NEG_COUGH = "./data/not_cough"
  
    #POS_SPEECH = "./data/speech"

    pos_cough = tf.data.Dataset.list_files(POS_COUGH+'\*.wav')
    neg_cough = tf.data.Dataset.list_files(NEG_COUGH+'\*.wav')
    
    #pos_speech = tf.data.Dataset.list_files(POS_SPEECH +'\*.wav')

    cough_labels = tf.data.Dataset.from_tensor_slices(tf.ones(len(pos_cough)))  
    
    not_cough_labels = tf.data.Dataset.from_tensor_slices(tf.ones(len(neg_cough))) 
    
    # Add labels and Combine Positive and Negative Samples
    cough = tf.data.Dataset.zip((pos_cough, cough_labels))
    
    not_cough = tf.data.Dataset.zip((neg_cough, not_cough_labels))
   
    negatives = not_cough
    positives = cough
    # join both sameples 
    data = positives.concatenate(negatives)

    ### 2. Create a Tensorflow Data Pipeline
    data = data.map(preprocess)
    data = data.cache()
    data = data.shuffle(buffer_size=1000)
    data = data.batch(16)
    data = data.prefetch(8)
    
    ## 3. Split data into train and test data
    train = data.take(int(len(data) * 0.7))
    test = data.skip(int(len(data) * 0.7)).take(int(len(data) - len(data) * 0.7))   #test.as_numpy_iterator().next()

    input_shape_spectrogram = (396, 65,1)
    model = get_CNN(input_shape_spectrogram)
    hist = model.fit(train, epochs=2, validation_data=test)

Answer 1

首先，您的数据集中需要有 3 个类，这意味着您需要区分喷嚏样本，就像您对咳嗽/非咳嗽所做的那样。然后，您需要将输出转换为一个热编码向量，其中除了与类索引对应的元素外，所有元素均为零。例如，如果你考虑不是咳嗽= 0，咳嗽= 1，打喷嚏= 2，则有喷嚏的样本必须是[0, 0, 1]，有咳嗽的样本必须是[0, 1, 0]，有咳嗽的样本必须是[0, 1, 0]没有咳嗽必须是 [1, 0, 0] 最后，你的外层应该有 3 个神经元。

model.add(Dense(3, activation='softmax'))