def get_text_sample(corpus_folder, min_sample_size):
corpus_docs = read_corpus(corpus_folder)
file = open("samples1.txt", "w")
for i in corpus_docs:
sentences = splitToSentences(i)
corpus_sentences = []
for sentence in sentences:
corpus_sentences.append(remove_char(sentence, '\n'))
text_size = len(corpus_sentences)
sample_size = math.ceil(text_size * .05)
if (sample_size < min_sample_size):
sample_size = min_sample_size
random_position = random.randint(0, text_size)
sample_text = ""
if (random_position + sample_size < text_size):
sample_text = get_substring(corpus_sentences, random_position,
random_position + sample_size)
else:
sample_text = get_substring(corpus_sentences, random_position,
text_size)
sample_text += get_substring(
corpus_sentences, 0,
sample_size - (text_size - random_position))
file.write(sample_text)
file.write('\n\n')
file.close()
from keras.models import load_model, model_from_json
import five_words as five
M = load_model("lyrical_lstm.h5")
from keras.models import load_model
import helper
import numpy as np
import sys
SEQUENCE_LENGTH = 40
SEQUENCE_STEP = 3
PATH_TO_CORPUS = "pink_floyd_lyrics.txt"
EPOCHS = 20
DIVERSITY = 1.0
text = helper.read_corpus(PATH_TO_CORPUS)
chars = helper.extract_characters(text)
sequences, next_chars = helper.create_sequences(text, SEQUENCE_LENGTH,
SEQUENCE_STEP)
char_to_index, indices_char = helper.get_chars_index_dicts(chars)
# load json and create model
json_file = open('model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# load weights into new model
loaded_model.load_weights("lyrical_lstm_weights.h5")
loaded_model.load_weights("new_weights.h5")
print("Loaded model from disk")
x = np.zeros((1, 40, 49))
warnings.simplefilter(action='ignore', category=FutureWarning)
import helper
import sys
import numpy as np
import tensorflow as tf
from pathlib import Path
from os.path import splitext
from os.path import basename
from keras.models import load_model
tf.logging.set_verbosity(tf.logging.ERROR)
CORPUS = helper.read_corpus(sys.argv[2])
PATH_TO_MODEL = sys.argv[1]
DIVERSITY = float(sys.argv[3])
GEN_LENGTH = 400
CHARS = helper.extract_characters(CORPUS)
char_to_index, indices_char = helper.get_chars_index_dicts(CHARS)
"""
Load the model
"""
modelFile = Path(PATH_TO_MODEL)
if modelFile.is_file():
model = load_model(PATH_TO_MODEL)
"""
GEN_LENGTH needs to be the same that was used when model was saved
"""
generated = ''