如何将代码从张量流转换为Keras

Question

我不熟悉keras，但我正在学习它。我需要帮助将tensorflow代码转换为keras代码。

labels = tf.placeholder(tf.float32, [batchSize, numClasses])
input_data = tf.placeholder(tf.int32, [batchSize, maxSeqLength])

print(labels)

data = tf.Variable(tf.zeros([batchSize, maxSeqLength, numDimensions]),dtype=tf.float32)
print(data)

data = tf.nn.embedding_lookup(wordVectors,input_data)
print(data)

lstmCell = tf.contrib.rnn.BasicLSTMCell(lstmUnits)
lstmCell = tf.contrib.rnn.DropoutWrapper(cell=lstmCell, output_keep_prob=0.1)

value, _ = tf.nn.dynamic_rnn(lstmCell, data, dtype=tf.float64)

data_mask = tf.cast(data, tf.bool)
data_len = tf.reduce_sum(tf.cast(data_mask, tf.float32), axis=1)
tf.nn.dynamic_rnn(lstmCell, data, sequence_length=data_len, initial_state=initial_state)