import argparse
import essen
import sys
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
from keras.models import Sequential
from keras.layers import Dense, Activation, LSTM
parser = argparse.ArgumentParser()
parser.add_argument("vocab_filename")
parser.add_argument("weights_file")
args = parser.parse_args()
maxlen = 3
idx_to_notes, notes_to_idx = essen.load_notes_vocab(args.vocab_filename)
stop_note = len(idx_to_notes)
vocab_size = len(idx_to_notes) + 1
idx_to_notes[stop_note] = (-1, "STOP_NOTE")
model = Sequential()
model.add(LSTM(200, return_sequences=False, input_shape=(maxlen, vocab_size)))
model.add(Dense(vocab_size))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
model.load_weights(args.weights_file)
starting_notes = [
notes_to_idx[(72, "1")], notes_to_idx[(60, "1/3")],
notes_to_idx[(73, "1/3")]
]
import argparse
import essen
import sys
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
from keras.models import Sequential
from keras.layers import Dense, Activation, LSTM
parser = argparse.ArgumentParser()
parser.add_argument("vocab_filename")
parser.add_argument("weights_file")
args = parser.parse_args()
maxlen = 3
idx_to_notes, notes_to_idx = essen.load_notes_vocab(args.vocab_filename)
stop_note = len(idx_to_notes)
vocab_size = len(idx_to_notes) + 1
idx_to_notes[stop_note] = (-1, "STOP_NOTE")
model = Sequential()
model.add(LSTM(200, return_sequences=False, input_shape=(maxlen, vocab_size)))
model.add(Dense(vocab_size))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
model.load_weights(args.weights_file)
starting_notes = [notes_to_idx[(72, "1")], notes_to_idx[(60, "1/3")], notes_to_idx[(73, "1/3")]]
x = np.zeros((1, maxlen, vocab_size), dtype=np.bool)
sys.stdout.write("Starting notes: ")
for i, note in enumerate(starting_notes):
def load_vocab(file):
idx_to_notes, notes_to_idx = essen.load_notes_vocab(file)
return idx_to_notes, notes_to_idx