python - ValueError being thrown 'This model has not been built'...for CNN Audio Spectrogram feature extraction

Question

In the code below, I am getting the error:

raise ValueError('This model has not yet been built. ' ValueError: This model has not yet been built. Build the model first by calling ``build()`` or calling ``fit()`` with some data, or specify an ``input_shape`` argument in the first layer(s) for automatic build.

I am trying to use a spectrogram instead of the Mel feature extraction for this CNN. I think the error may be in the extraction process for the extract_features step.

Any help will be greatly appreciated in figuring out the source of this error.

Here are some sizes of arrays generated before the error:

x_test = {ndarray:(353,128)} x_train = {ndarray:(1408,128)} y = {ndarray:(1761,)} y_test = {ndarray:(353,10)} y_ttrain = {ndarray:(1408,10)}

CODE

# Sample rate conversion
import librosa
import librosa.display
from scipy.io import wavfile as wav
import numpy as np
import pandas as pd
import os

import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()

max_pad_len = 174
n_mels = 128

def extract_features(file_name):
    try:
        audio, sample_rate = librosa.core.load(file_name, res_type='kaiser_fast')
        mely = librosa.feature.melspectrogram(y=audio, sr=sample_rate, n_mels=n_mels)
        # pad_width = max_pad_len - mely.shape[1]
        # mely = np.pad(mely, pad_width=((0, 0), (0, pad_width)), mode='constant')
        melyscaled = np.mean(mely.T, axis=0)

    except Exception as e:
        print("Error encountered while parsing file: ", file_name)
        return None

    return melyscaled

features = []

# Iterate through each sound file and extract the features

from time import sleep

#from tqdm import tqdm
from alive_progress import alive_bar
items = len(metadata.index)
with alive_bar(items) as bar:
    for index, row in metadata.iterrows():
            bar()
            file_name = os.path.join(os.path.abspath(fulldatasetpath), 'fold' + str(row["fold"]) + '/',
                                     str(row["slice_file_name"]))

            class_label = row["class_name"]
            data = extract_features(file_name)

            features.append([data, class_label])

# Convert into a Panda dataframe
featuresdf = pd.DataFrame(features, columns=['feature', 'class_label'])

print('Finished feature extraction from ', len(featuresdf), ' files')

from sklearn.preprocessing import LabelEncoder
from keras.utils import to_categorical

# Convert features and corresponding classification labels into numpy arrays
X = np.array(featuresdf.feature.tolist())
y = np.array(featuresdf.class_label.tolist())

# Encode the classification labels
le = LabelEncoder()
yy = to_categorical(le.fit_transform(y))

# split the dataset
from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(X, yy, test_size=0.2, random_state = 42)

### Convolutional Neural Network (CNN) model architecture
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, Conv2D, MaxPooling2D, GlobalAveragePooling2D
from keras.optimizers import Adam
from keras.utils import np_utils
from sklearn import metrics

num_rows = 40
num_columns = 174
num_channels = 1
#
#x_train = x_train.reshape(x_train.shape[0], num_rows, num_columns, num_channels)
#x_test = x_test.reshape(x_test.shape[0], num_rows, num_columns, num_channels)

num_labels = yy.shape[1]
filter_size = 2

# Construct model
model = Sequential()
#model.add(Conv2D(filters=16, kernel_size=2, input_shape=(num_rows, num_columns, num_channels), activation='relu'))
model.add(Conv2D(filters=16, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=32, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=64, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=128, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))
model.add(GlobalAveragePooling2D())

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

model.compile(loss='categorical_crossentropy', metrics=['accuracy'], optimizer='adam')

# Display model architecture summary
model.summary()

Answer 1

You have to build your model with your input shape before calling model.summary():

model.build((128,))