diff options
3 files changed, 3 insertions, 3 deletions
diff --git a/tensorflow/examples/learn/text_classification.py b/tensorflow/examples/learn/text_classification.py index 7ad77787ab..a26cdefda8 100644 --- a/tensorflow/examples/learn/text_classification.py +++ b/tensorflow/examples/learn/text_classification.py @@ -60,7 +60,7 @@ def rnn_model(features, target): # Split into list of embedding per word, while removing doc length dim. # word_list results to be a list of tensors [batch_size, EMBEDDING_SIZE]. - word_list = tf.unpack(word_vectors, axis=1) + word_list = tf.unstack(word_vectors, axis=1) # Create a Gated Recurrent Unit cell with hidden size of EMBEDDING_SIZE. cell = tf.nn.rnn_cell.GRUCell(EMBEDDING_SIZE) diff --git a/tensorflow/examples/learn/text_classification_builtin_rnn_model.py b/tensorflow/examples/learn/text_classification_builtin_rnn_model.py index 79654eb902..aaa6b53e3f 100644 --- a/tensorflow/examples/learn/text_classification_builtin_rnn_model.py +++ b/tensorflow/examples/learn/text_classification_builtin_rnn_model.py @@ -42,7 +42,7 @@ def input_op_fn(features): features, vocab_size=n_words, embed_dim=EMBEDDING_SIZE, scope='words') # Split into list of embedding per word, while removing doc length dim. # word_list results to be a list of tensors [batch_size, EMBEDDING_SIZE]. - word_list = tf.unpack(word_vectors, axis=1) + word_list = tf.unstack(word_vectors, axis=1) return word_list diff --git a/tensorflow/examples/learn/text_classification_character_rnn.py b/tensorflow/examples/learn/text_classification_character_rnn.py index bca3df4c04..485d7592c4 100644 --- a/tensorflow/examples/learn/text_classification_character_rnn.py +++ b/tensorflow/examples/learn/text_classification_character_rnn.py @@ -48,7 +48,7 @@ def char_rnn_model(features, target): """Character level recurrent neural network model to predict classes.""" target = tf.one_hot(target, 15, 1, 0) byte_list = tf.ont_hot(features, 256, 1, 0) - byte_list = tf.unpack(byte_list, axis=1) + byte_list = tf.unstack(byte_list, axis=1) cell = tf.nn.rnn_cell.GRUCell(HIDDEN_SIZE) _, encoding = tf.nn.rnn(cell, byte_list, dtype=tf.float32) |