def test_interpret_one_hot_on_A0(self):
midi_pitch_input = 21
one_hot = encoder.one_hot_encode_midi_pitch(midi_pitch_input)
print()
midi_pitch_output = encoder.interpret_one_hot(one_hot, printing=True)
print(
f'midi_pitch_input: {midi_pitch_input:>3} midi_pitch_output: {midi_pitch_output:>3}'
)
self.assertEqual(midi_pitch_input, midi_pitch_output)
def test_interpret_one_hot_on_rest(self):
midi_pitch_input = encoder.REST_MIDI_ENCODING
one_hot = encoder.one_hot_encode_midi_pitch(midi_pitch_input)
print()
midi_pitch_output = encoder.interpret_one_hot(one_hot, printing=True)
print(
f'midi_pitch_input: {midi_pitch_input:>3} midi_pitch_output: {midi_pitch_output:>3}'
)
self.assertEqual(midi_pitch_input, midi_pitch_output)
def test_interpret_one_hot_on_putting_lows_last(self):
midi_pitch_input = 60
one_hot = encoder.one_hot_encode_midi_pitch(midi_pitch_input,
low_last=True)
print()
midi_pitch_output = encoder.interpret_one_hot(one_hot,
low_last=True,
printing=True)
print(
f'midi_pitch_input: {midi_pitch_input:>3} midi_pitch_output: {midi_pitch_output:>3}'
)
self.assertEqual(midi_pitch_input, midi_pitch_output)
def show_example_prediction(model_name,
i=0,
version=1,
x_val=None,
y_val=None,
printing_in_full=False):
if x_val is None or y_val is None:
_, _, x_val, y_val = load_data_arrays(version)
example = (x_val[i], y_val[i])
model_input = example[0].reshape(1, example[0].shape[0], 1)
example_prediction = load_model_and_get_predictions(
model_name, model_input)[0]
example_ground_truth = example[1]
i_prediction = np.argmax(example_prediction)
i_ground_truth = np.argmax(example_ground_truth)
midi_pitch_prediction = interpret_one_hot(example_prediction)
midi_pitch_ground_truth = interpret_one_hot(example_ground_truth)
note_name_prediction = get_note_name(midi_pitch_prediction)
note_name_ground_truth = get_note_name(midi_pitch_ground_truth)
if printing_in_full:
print(f'\nmodel_input: {model_input.shape}')
print(model_input)
print(f'\nexample_prediction: {example_prediction.shape}')
print(example_prediction)
print(f'\nexample_ground_truth: {example_ground_truth.shape}')
print(example_ground_truth)
print()
print(f'val instance {i}')
print(
f' i_prediction: {i_prediction:>4} i_ground_truth: {i_ground_truth:>4}'
)
print(
f'midi_pitch_prediction: {midi_pitch_prediction:>4} midi_pitch_ground_truth: {midi_pitch_ground_truth:>4}'
)
print(
f' note_name_prediction: {note_name_prediction:>4} note_name_ground_truth: {note_name_ground_truth:>4}'
)
def plot_wav_prediction(note,
example,
model_name,
method='scipy',
printing=False,
plotting_spectrogram=False,
showing=True):
wav_file = f'wav_files/single_{note}_{example}.wav'
model = load_model(model_name)
if method == 'scipy':
if plotting_spectrogram:
_, times, spectrogram = plot_spectrogram(wav_file,
strategy='scipy',
showing=False)
else:
_, times, spectrogram = get_spectrogram(wav_file, strategy='scipy')
else:
if plotting_spectrogram:
_, times, spectrogram = plot_spectrogram(wav_file,
strategy='pyplot',
showing=False)
else:
_, times, spectrogram = get_spectrogram(wav_file,
strategy='pyplot')
if printing:
print(spectrogram.shape)
midi_pitch_predictions = np.zeros(spectrogram.shape[1])
for i in range(spectrogram.shape[1]):
periodogram = spectrogram[:, i].reshape(1, spectrogram.shape[0], 1)
pitch_probabilities = model.predict(periodogram)[0]
midi_pitch_predictions[i] = interpret_one_hot(pitch_probabilities)
if printing:
print(midi_pitch_predictions[i])
print(pitch_probabilities)
plt.figure()
plt.title(f'Prediction of \"{wav_file}\"\nby model \"{model_name}\"')
plt.plot(times, midi_pitch_predictions)
plt.xlabel('time (seconds)')
plt.ylabel('MIDI pitch')
plt.ylim(-2, 109)
if showing:
plt.show()
def predict_each_window_of_wav_file(file_name,
wav_path='wav_files',
adding_spectral_powers=True,
normalising=True,
window_size=25,
model_name=None,
printing=False):
if wav_path is None:
wav_file_full_path = f'{file_name}.wav'
else:
wav_file_full_path = f'{wav_path}/{file_name}.wav'
# get the spectrogram of the file and swap the axes to get an array of periodograms
_, _, spectrogram = get_spectrogram(wav_file_full_path,
window_size=window_size)
periodograms = np.swapaxes(spectrogram, 0, 1)
if adding_spectral_powers:
periodograms = add_spectral_powers(periodograms)
periodograms = periodograms.reshape(
(periodograms.shape[0], periodograms.shape[1], 1))
if normalising:
periodograms = normalise(
periodograms,
spectral_powers_present=adding_spectral_powers,
first_order_differences_present=False)
# load the specified model and use it to predict the pitch at each window
model = load_model(model_name)
probabilities = model.predict(periodograms)
predictions = np.empty(len(probabilities), dtype=object)
for i in range(len(probabilities)):
predictions[i] = interpret_one_hot(probabilities[i], encoding=None)
if printing:
print(predictions.shape)
print(predictions)
return predictions
def create_comparison_text_file(file_name,
model_name,
window_size=50,
wav_path='wav_files',
xml_path='xml_files',
adding_spectral_powers=True,
normalising=True,
save_name=None,
printing=False):
if save_name is None:
save_name = file_name
if wav_path is None:
wav_file_full_path = f'{file_name}.wav'
else:
wav_file_full_path = f'{wav_path}/{file_name}.wav'
# get the ground-truth pitch for the file
ground_truth = get_monophonic_ground_truth(file_name,
wav_path=wav_path,
xml_path=xml_path,
window_size=window_size)
# get the spectrogram of the file and swap the axes to get an array of periodograms
_, _, spectrogram = get_spectrogram(wav_file_full_path,
window_size=window_size)
periodograms = np.swapaxes(spectrogram, 0, 1)
if adding_spectral_powers:
periodograms = add_spectral_powers(periodograms)
periodograms = periodograms.reshape(
(periodograms.shape[0], periodograms.shape[1], 1))
if normalising:
periodograms = normalise(
periodograms,
spectral_powers_present=adding_spectral_powers,
first_order_differences_present=False)
# load the specified model and use it to predict the pitch at each window
model = load_model(model_name)
probabilities = model.predict(periodograms)
predictions = np.empty(len(probabilities), dtype=object)
for i in range(len(probabilities)):
predictions[i] = interpret_one_hot(probabilities[i], encoding=None)
# write the ground truth pitches and pitch predictions to a text file
f = open(f'txt_files/{save_name}.txt', 'w')
f.write(' time step: ')
for time_step in range(len(ground_truth)):
f.write(f'{time_step:<5}')
f.write('\n')
f.write(' ground truth: ')
for pitch in ground_truth:
f.write(f'{pitch:<5}')
f.write('\n')
f.write('model predictions: ')
for pitch in predictions:
f.write(f'{pitch:<5}')
f.close()
if printing:
print(spectrogram.shape)
print(spectrogram)
print()
print(predictions.shape)
print(predictions)
print()
print(ground_truth.shape)
print(ground_truth)