data = generator(...)
model = init_model(...)
for i in range(NUM):
  x, y = next(data)
  _y = model.predict(x)
  shape = _y.shape
  input_length = np.ones(shape[0]) * shape[1]
  ctc_decode = K.ctc_decode(_y, input_length)[0][0]
  out = K.get_value(ctc_decode)

data = generator(...)
model = init_model(...)
x = model.output  # [batch_sizes, series_length, classes]
input_length = KL.Input(batch_shape=[None], dtype='int32')
ctc_decode = K.ctc_decode(x, input_length=input_length * K.shape(x)[1])
decode = K.function([model.input, input_length], [ctc_decode[0][0]])
for i in range(NUM):
  _x, _y = next(data)
  out = decode([_x, np.ones(1)])

from keras import backend as K
from keras.layers import Lambda,Input
from keras import Model
from tensorflow.python.ops import ctc_ops as ctc
import tensorflow as tf
from keras.layers import Layer
class CTC_Batch_Cost():
  '''
  用于計算CTC loss
  '''
  def ctc_lambda_func(self,args):
    """Runs CTC loss algorithm on each batch element.

    # Arguments
      y_true: tensor `(samples, max_string_length)` 真實標簽
      y_pred: tensor `(samples, time_steps, num_categories)` 預(yù)測前未經(jīng)過softmax的向量
      input_length: tensor `(samples, 1)` 每一個y_pred的長度
      label_length: tensor `(samples, 1)` 每一個y_true的長度

      # Returns
        Tensor with shape (samples,1) 包含了每一個樣本的ctc loss
      """
    y_true, y_pred, input_length, label_length = args

    # y_pred = y_pred[:, :, :]
    # y_pred = y_pred[:, 2:, :]
    return self.ctc_batch_cost(y_true, y_pred, input_length, label_length)

  def __call__(self, args):
    '''
    ctc_decode 每次創(chuàng)建會生成一個節(jié)點，這里參考了上面的內(nèi)容
    將ctc封裝成模型，是否會解決這個問題還沒有測試過這種方法是否還會出現(xiàn)創(chuàng)建節(jié)點的問題
    '''
    y_true = Input(shape=(None,))
    y_pred = Input(shape=(None,None))
    input_length = Input(shape=(1,))
    label_length = Input(shape=(1,))

    lamd = Lambda(self.ctc_lambda_func, output_shape=(1,), name='ctc')([y_true,y_pred,input_length,label_length])
    model = Model([y_true,y_pred,input_length,label_length],[lamd],name="ctc")

    # return Lambda(self.ctc_lambda_func, output_shape=(1,), name='ctc')(args)
    return model(args)

  def ctc_batch_cost(self,y_true, y_pred, input_length, label_length):
    """Runs CTC loss algorithm on each batch element.

    # Arguments
      y_true: tensor `(samples, max_string_length)`
        containing the truth labels.
      y_pred: tensor `(samples, time_steps, num_categories)`
        containing the prediction, or output of the softmax.
      input_length: tensor `(samples, 1)` containing the sequence length for
        each batch item in `y_pred`.
      label_length: tensor `(samples, 1)` containing the sequence length for
        each batch item in `y_true`.

    # Returns
      Tensor with shape (samples,1) containing the
        CTC loss of each element.
    """
    label_length = tf.to_int32(tf.squeeze(label_length, axis=-1))
    input_length = tf.to_int32(tf.squeeze(input_length, axis=-1))
    sparse_labels = tf.to_int32(K.ctc_label_dense_to_sparse(y_true, label_length))

    y_pred = tf.log(tf.transpose(y_pred, perm=[1, 0, 2]) + 1e-7)

    # 注意這里的True是為了忽略解碼失敗的情況，此時loss會變成nan直到下一個個batch
    return tf.expand_dims(ctc.ctc_loss(inputs=y_pred,
                      labels=sparse_labels,
                      sequence_length=input_length,
                      ignore_longer_outputs_than_inputs=True), 1)

# 使用方法:(注意shape)
loss_out = CTC_Batch_Cost()([y_true, y_pred, audio_length, label_length])

from keras import backend as K
from keras.layers import Lambda,Input
from keras import Model
from tensorflow.python.ops import ctc_ops as ctc
import tensorflow as tf
from keras.layers import Layer

class CTCDecodeLayer(Layer):

  def __init__(self, **kwargs):
    super().__init__(**kwargs)

  def _ctc_decode(self,args):
    base_pred, in_len = args
    in_len = K.squeeze(in_len,axis=-1)

    r = K.ctc_decode(base_pred, in_len, greedy=True, beam_width=100, top_paths=1)
    r1 = r[0][0]
    prob = r[1][0]
    return [r1,prob]

  def call(self, inputs, **kwargs):
    return self._ctc_decode(inputs)

  def compute_output_shape(self, input_shape):
    return [(None,None),(1,)]

class CTCDecode():
  '''用與CTC 解碼，得到真實語音序列
      2019年7月18日所寫，對ctc_decode使用模型進行了封裝，從而在初始化完成后不會再有新節(jié)點的產(chǎn)生
  '''
  def __init__(self):
    base_pred = Input(shape=[None,None],name="pred")
    feature_len = Input(shape=[1,],name="feature_len")
    r1, prob = CTCDecodeLayer()([base_pred,feature_len])
    self.model = Model([base_pred,feature_len],[r1,prob])
    pass

  def ctc_decode(self,base_pred,in_len,return_prob = False):
    '''
    :param base_pred:[sample,timestamp,vector]
    :param in_len: [sample,1]
    :return:
    '''
    result,prob = self.model.predict([base_pred,in_len])
    if return_prob:
      return result,prob
    return result

  def __call__(self,base_pred,in_len,return_prob = False):
    return self.ctc_decode(base_pred,in_len,return_prob)


# 使用方法：(注意shape，是batch級的輸入)
ctc_decoder = CTCDecode()
ctc_decoder.ctc_decode(result,feature_len)