from poi_detector.src.dataset.e_create_dataset.Classes.output_handler import OutputDatasetHandler
from poi_detector.src.dataset.e_create_dataset.Classes.data_balancer import DatasetBalancer
from os.path import join as os_path_join
base_dir = 'D:/Documents/Thesis/Project Skaterbot/Datasets/Library/'
transform_type = 'spectrogram'
time_size = 1000
freq_size = 20
window_size = 100
dataset_dir = os_path_join(base_dir, str(window_size))
input_handler = InputDatasetHandler(transform_type, window_size)
output_handler = OutputDatasetHandler(window_size)
balancer = DatasetBalancer()
names, pois_lists = get_data_from_csv(relative_locator_csv_path)
n_samples = names.shape[0]
i = 0
for name, pois_list in zip(names, pois_lists):
i += 1
try:
print('Trying', i, 'out of', n_samples, '.')
""" CREATE SPECTROGRAM """
spectrogram = input_handler.calculate_input(name, 'spectrogram', 512)
balancer.save_input(dataset_dir, name + 'spectrogram', spectrogram)
""" CREATE MEL-SPECTROGRAM """
melspectrogram = input_handler.calculate_input(name, 'melspectrogram', 256)
balancer.save_input(dataset_dir, name + 'melspectrogram', melspectrogram)
base_dir = 'D:/Documents/Thesis/Project Skaterbot/Datasets/Library/'
transform_type = 'cqt'
freq_size = 512
window_size = 10
dataset_dir = os_path_join(base_dir, 'window_size_' + str(window_size))
data_dir = os_path_join(dataset_dir, 'data')
try:
os_mkdir(data_dir)
except FileExistsError:
pass
input_handler = InputDatasetHandler(transform_type, window_size)
names, pois_lists = get_data_from_csv(preciser_csv_path)
sample_name = names[randint(0, names.shape[0])]
try:
print('Trying:', sample_name)
""" CREATE CQT """
audio_data, sr = librosa.load(ospathjoin(wav_dir, sample_name), sr=44100)
spectrogram = Transform.get_bad_spectrogram(audio_data, sr, freq_size, window_size)
spectrogram = np.flip(spectrogram, axis=0)
spec_dir = 'D:\Documents\Thesis\THESIS CHAPTERS\Chapter 2 - AUDIO AND TRANSFORMS'
spec_path = ospathjoin(spec_dir, sample_name)
skimage.io.imsave(spec_path + '_bad.jpg', spectrogram[:, 1000: 1512])
from __future__ import absolute_import, division, print_function, unicode_literals
#from ..basic_classes.constants import wav_dir, preciser_csv_path, mels_dir
from poi_detector.src.basic_classes.constants import wav_dir, preciser_csv_path, mels_dir
from poi_detector.src.basic_classes.helper import get_data_from_csv
from poi_detector.src.basic_classes.transforms import calculate_transform
import numpy as np
import librosa
import pickle
""" Get Input-names and Output-Points of Interest """
# the last csv that is used has all songs shuffled. No need to process input names.
input_names, output_pois = get_data_from_csv(preciser_csv_path)
n_samples = input_names.shape[0]
transform_dir = mels_dir
failed = []
min_val = 1000000000000000000000000
max_val = -100000000000000000000000
for i in range(n_samples):
sample_name = input_names[i]
output_sample = output_pois[i]
print(sample_name)
try:
wav, sr = librosa.load(wav_dir + sample_name, mono=True, sr=44100)
transformed_x = calculate_transform(wav, sr, 'melspectrogram', 512)
print(transformed_x.shape)
print(min_val, max_val)
trans_max = np.amax(transformed_x)
if trans_max > max_val:
max_val = trans_max