From e865f17a0d0bbb370788fc3d0a67c54d2ec5cf82 Mon Sep 17 00:00:00 2001 From: Malar Kannan Date: Fri, 20 Oct 2017 12:52:11 +0530 Subject: [PATCH] pickling intermediate data to save memory usage --- .gitignore | 1 + speech_data.py | 39 +++++++++++++++++++++++++++++++++++---- speech_siamese.py | 4 ++-- 3 files changed, 38 insertions(+), 6 deletions(-) diff --git a/.gitignore b/.gitignore index 82977a3..b79ceae 100644 --- a/.gitignore +++ b/.gitignore @@ -140,3 +140,4 @@ Temporary Items outputs/* inputs/mnist inputs/audio* +*.pkl diff --git a/speech_data.py b/speech_data.py index a7cb35c..f82b330 100644 --- a/speech_data.py +++ b/speech_data.py @@ -2,7 +2,7 @@ import pandas as pd import numpy as np from spectro_gen import generate_aiff_spectrogram from sklearn.model_selection import train_test_split -import tensorflow as tf +import pickle,gc def sunflower_data(): audio_samples = pd.read_csv('./outputs/audio.csv',names=['word','voice','rate','variant','file']) @@ -62,11 +62,12 @@ def create_spectrogram_data(audio_group='audio'): audio_samples.loc[:,'spectrogram'] = audio_samples.loc[:,'file'].apply(lambda x:'outputs/'+audio_group+'/'+x).apply(generate_aiff_spectrogram) audio_samples.to_pickle('outputs/spectrogram.pkl') -def speech_pairs_data(audio_group='audio'): +def create_speech_pairs_data(audio_group='audio'): audio_samples = pd.read_pickle('outputs/spectrogram.pkl') y_data = audio_samples['variant'].apply(lambda x:x=='normal').values max_samples = audio_samples['spectrogram'].apply(lambda x:x.shape[0]).max() sample_size = audio_samples['spectrogram'][0].shape[1] + pickle.dump((max_samples,sample_size),open('./spectrogram_vars.pkl','wb')) audio_samples_pos = audio_samples[audio_samples['variant'] == 'normal'].reset_index(drop=True) audio_samples_neg = audio_samples[audio_samples['variant'] == 'phoneme'].reset_index(drop=True) def append_zeros(spgr): @@ -74,17 +75,47 @@ def speech_pairs_data(audio_group='audio'): def create_data(sf): sample_count = sf['spectrogram'].shape[0] pad_sun = sf['spectrogram'].apply(append_zeros).values + print('appended zeros') x_data = np.vstack(pad_sun).reshape((sample_count,max_samples,sample_size)) + print('reshaped') return x_data + print('creating speech pair data') x_data_pos = create_data(audio_samples_pos) x_data_neg = create_data(audio_samples_neg) + np.save('outputs/x_data_pos.npy',x_data_pos) + np.save('outputs/x_data_neg.npy',x_data_neg) + print('pickled speech pairs') + +def create_speech_model_data(): + (max_samples,sample_size) = pickle.load(open('./spectrogram_vars.pkl','rb')) + x_data_pos = np.load('outputs/x_data_pos.npy') + x_data_neg = np.load('outputs/x_data_neg.npy') x_pos_train, x_pos_test, x_neg_train, x_neg_test =train_test_split(x_data_pos,x_data_neg,test_size=0.33) + del x_data_pos + del x_data_neg + gc.collect() + print('split train and test') tr_y = np.array(x_pos_train.shape[0]*[[1,0]]) te_y = np.array(x_pos_test.shape[0]*[[1,0]]) tr_pairs = np.array([x_pos_train,x_neg_train]).reshape(x_pos_train.shape[0],2,max_samples,sample_size) te_pairs = np.array([x_pos_test,x_neg_test]).reshape(x_pos_test.shape[0],2,max_samples,sample_size) + print('reshaped to input dim') + np.save('outputs/tr_pairs.npy',tr_pairs) + np.save('outputs/te_pairs.npy',te_pairs) + np.save('outputs/tr_y.npy',tr_y) + np.save('outputs/te_y.npy',te_y) + print('pickled speech model data') + # return tr_pairs,te_pairs,tr_y,te_y + +def speech_model_data(): + tr_pairs = np.load('outputs/tr_pairs.npy') + te_pairs = np.load('outputs/te_pairs.npy') + tr_y = np.load('outputs/tr_y.npy') + te_y = np.load('outputs/te_y.npy') return tr_pairs,te_pairs,tr_y,te_y if __name__ == '__main__': - create_spectrogram_data() - print(speech_pairs_data()) + #create_spectrogram_data() + # create_speech_pairs_data() + # create_speech_model_data() + print(speech_model_data()) diff --git a/speech_siamese.py b/speech_siamese.py index 821d29a..aaf3256 100644 --- a/speech_siamese.py +++ b/speech_siamese.py @@ -16,7 +16,7 @@ import numpy as np import random # from keras.datasets import mnist -from speech_data import sunflower_pairs_data +from speech_data import speech_model_data from keras.models import Model from keras.layers import Dense, Dropout, Input, Lambda, LSTM, SimpleRNN from keras.optimizers import RMSprop @@ -66,7 +66,7 @@ def accuracy(y_true, y_pred): # the data, shuffled and split between train and test sets -tr_pairs,te_pairs,tr_y,te_y = sunflower_pairs_data() +tr_pairs,te_pairs,tr_y,te_y = speech_model_data() # y_train.shape,y_test.shape # x_train.shape,x_test.shape # x_train = x_train.reshape(60000, 784)