def main(ms_file_name, line_freq, ouptut_file):
tf.reset_default_graph()
sess = tf.InteractiveSession()
# load vocabulary
int2word = read_vocab("models/vocabulary_semantic.txt")
# Restore weights
model = "models/semantic_model.meta"
saver = tf.train.import_meta_graph(model)
saver.restore(sess, model[:-5])
graph = tf.get_default_graph()
model_input = graph.get_tensor_by_name("model_input:0")
seq_len = graph.get_tensor_by_name("seq_lengths:0")
rnn_keep_prob = graph.get_tensor_by_name("keep_prob:0")
height_tensor = graph.get_tensor_by_name("input_height:0")
width_reduction_tensor = graph.get_tensor_by_name("width_reduction:0")
logits = tf.get_collection("logits")[0]
# Constants that are saved inside the model itself
WIDTH_REDUCTION, HEIGHT = sess.run([width_reduction_tensor, height_tensor])
decoded, _ = tf.nn.ctc_greedy_decoder(logits, seq_len)
# split the music score into lines
print(f"Process {ms_file_name}\n")
lines = split_score(ms_file_name, line_freq)
output = open(ouptut_file, "w")
# process save file
for idx, line in enumerate(lines):
# write the file to sample directory for sampling
print(f"./samples/sample{idx}.png\n")
cv2.imwrite(f"./samples/sample{idx}.png", line)
gray = cv2.cvtColor(line, cv2.COLOR_BGR2GRAY)
image = ctc_utils.resize(gray, HEIGHT)
image = ctc_utils.normalize(image)
image = np.asarray(image).reshape(1, image.shape[0], -1, 1)
seq_lengths = [image.shape[2] / WIDTH_REDUCTION]
prediction = sess.run(decoded,
feed_dict={
model_input: image,
seq_len: seq_lengths,
rnn_keep_prob: 1.0,
})
str_predictions = ctc_utils.sparse_tensor_to_strs(prediction)
for w in str_predictions[0]:
description = int2word[w]
notation, v1, v2 = parse_description(description)
if v1 != "tie":
if notation == "barline":
output.write("### ----------------\n")
elif notation == "note" or notation == "gracenote":
output.write(f'- ["{notation}", "{v1}", "{v2}"]\n')
elif notation == "rest":
output.write(f'- ["rest", "{v1}"]\n')
output.close()
image = cv2.imread(imgpath, 0)
image = ctc_utils.resize(image, HEIGHT)
image = ctc_utils.normalize(image)
image = np.asarray(image).reshape(1, image.shape[0], image.shape[1], 1)
seq_lengths = [image.shape[2] / WIDTH_REDUCTION]
prediction = sess.run(decoded,
feed_dict={
input: image,
seq_len: seq_lengths,
rnn_keep_prob: 1.0,
})
str_predictions = ctc_utils.sparse_tensor_to_strs(prediction)
output = ""
for w in str_predictions[0]:
output += str(int2word[w])
output += str('\t')
output.rstrip()
f = open(f'{corpus}/{x_in}/{x_in}.txt', "r")
inputt = f.read()
f.close
res2 = " "
for x in inputt:
res2 += x.strip()
def predict(image):
tf.reset_default_graph()
sess = tf.InteractiveSession()
voc_file = 'vocabulary_agnostic.txt'
model = './Models/model.hdf5-69000.meta'
# Read the dictionary
dict_file = open(voc_file, "r")
dict_list = dict_file.read().splitlines()
int2word = dict()
for word in dict_list:
word_idx = len(int2word)
int2word[word_idx] = word
dict_file.close()
# Restore weights
saver = tf.train.import_meta_graph(model)
saver.restore(sess, model[:-5])
graph = tf.get_default_graph()
input = graph.get_tensor_by_name("model_input:0")
seq_len = graph.get_tensor_by_name("seq_lengths:0")
rnn_keep_prob = graph.get_tensor_by_name("keep_prob:0")
height_tensor = graph.get_tensor_by_name("input_height:0")
width_reduction_tensor = graph.get_tensor_by_name("width_reduction:0")
logits = tf.get_collection("logits")[0]
# Constants that are saved inside the model itself
WIDTH_REDUCTION, HEIGHT = sess.run([width_reduction_tensor, height_tensor])
decoded, _ = tf.nn.ctc_greedy_decoder(logits, seq_len)
image = cv2.imread(image, False)
image = ctc_utils.resize(image, HEIGHT)
image = ctc_utils.normalize(image)
image = np.asarray(image).reshape(1, image.shape[0], image.shape[1], 1)
seq_lengths = [image.shape[2] / WIDTH_REDUCTION]
prediction = sess.run(
decoded, feed_dict={input: image, seq_len: seq_lengths, rnn_keep_prob: 1.0,}
)
str_predictions = ctc_utils.sparse_tensor_to_strs(prediction)
notes = []
for w in str_predictions[0]:
temp = int2word[w].split('.')
print(temp)
if (len(temp) != 2):
continue
else:
symbol, des = temp
if (symbol == 'note'):
length, note = des.split('-', 1)
if ('beamed' in length):
length = 'eigth'
notes.append((length, notes_dict[note]))
elif (symbol == 'rest'):
length, _ = des.split('-', 1)
notes.append((length, 'rest'))
return notes
