| /external/tensorflow/tensorflow/contrib/seq2seq/python/kernel_tests/ |
| D | basic_decoder_test.py | 133 vocabulary_size = 7
134 cell_depth = vocabulary_size # cell's logits must match vocabulary size
136 start_tokens = np.random.randint(0, vocabulary_size, size=batch_size)
140 embeddings = np.random.randn(vocabulary_size,
142 cell = rnn_cell.LSTMCell(vocabulary_size)
205 vocabulary_size = 7
206 cell_depth = vocabulary_size # cell's logits must match vocabulary size
209 start_tokens = np.random.randint(0, vocabulary_size, size=batch_size)
216 embeddings = np.random.randn(vocabulary_size,
218 cell = rnn_cell.LSTMCell(vocabulary_size)
[all …]
|
| /external/tensorflow/tensorflow/python/estimator/ |
| D | warm_starting_util_test.py | 378 "sc_vocab", vocabulary_file=vocab_path, vocabulary_size=4)
415 "sc_vocab", vocabulary_file=vocab_path, vocabulary_size=4)
461 "sc_vocab", vocabulary_file=current_vocab_path, vocabulary_size=2)
484 new_vocab_size=sc_vocab.vocabulary_size,
546 "sc_vocab", vocabulary_file=vocab_path, vocabulary_size=4)
606 new_vocab_size=sc_vocab.vocabulary_size,
640 "sc_vocab", vocabulary_file=new_vocab_path, vocabulary_size=6)
668 new_vocab_size=sc_vocab.vocabulary_size,
709 "sc_vocab", vocabulary_file=new_vocab_path, vocabulary_size=6)
732 new_vocab_size=sc_vocab.vocabulary_size,
[all …]
|
| /external/tensorflow/tensorflow/examples/tutorials/word2vec/ |
| D | word2vec_basic.py | 89 vocabulary_size = 50000 variable
118 vocabulary, vocabulary_size)
192 tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
199 [vocabulary_size, embedding_size],
202 nce_biases = tf.Variable(tf.zeros([vocabulary_size]))
217 num_classes=vocabulary_size))
302 for i in xrange(vocabulary_size):
|
| /external/tensorflow/tensorflow/python/feature_column/ |
| D | feature_column_test.py | 2324 key='aaa', vocabulary_file='path_to_file', vocabulary_size=3)
2335 key='aaa', vocabulary_file='path_to_file', vocabulary_size=3,
2344 key='aaa', vocabulary_file='path_to_file', vocabulary_size=3,
2356 key='aaa', vocabulary_file=None, vocabulary_size=3)
2361 key='aaa', vocabulary_file='', vocabulary_size=3)
2365 key='aaa', vocabulary_file='file_does_not_exist', vocabulary_size=10)
2379 vocabulary_size=-1)
2383 vocabulary_size=0)
2389 vocabulary_size=self._wire_vocabulary_size + 1)
2402 key='aaa', vocabulary_file='path', vocabulary_size=3,
[all …]
|
| D | feature_column.py | 1043 vocabulary_size=None, argument
1129 if vocabulary_size is None:
1134 vocabulary_size = sum(1 for _ in f)
1137 'in the vocabulary_file %s.', vocabulary_size, key, vocabulary_file)
1140 if vocabulary_size < 1:
1154 vocabulary_size=vocabulary_size,
2499 vocab_size=self.vocabulary_size,
2507 return self.vocabulary_size + self.num_oov_buckets
|
| /external/tensorflow/tensorflow/python/keras/_impl/keras/preprocessing/ |
| D | sequence_test.py | 85 np.arange(3), vocabulary_size=3)
91 np.arange(5), vocabulary_size=5, window_size=1, categorical=True)
|
| D | sequence.py | 145 vocabulary_size, argument
215 random.randint(1, vocabulary_size - 1)]
|
| /external/tensorflow/tensorflow/examples/udacity/ |
| D | 6_lstm.ipynb | 300 "vocabulary_size = len(string.ascii_lowercase) + 1 # [a-z] + ' '\n",
395 " batch = np.zeros(shape=(self._batch_size, vocabulary_size), dtype=np.float)\n",
479 " p = np.zeros(shape=[1, vocabulary_size], dtype=np.float)\n",
485 " b = np.random.uniform(0.0, 1.0, size=[1, vocabulary_size])\n",
522 " ix = tf.Variable(tf.truncated_normal([vocabulary_size, num_nodes], -0.1, 0.1))\n",
526 " fx = tf.Variable(tf.truncated_normal([vocabulary_size, num_nodes], -0.1, 0.1))\n",
530 " cx = tf.Variable(tf.truncated_normal([vocabulary_size, num_nodes], -0.1, 0.1))\n",
534 " ox = tf.Variable(tf.truncated_normal([vocabulary_size, num_nodes], -0.1, 0.1))\n",
541 " w = tf.Variable(tf.truncated_normal([num_nodes, vocabulary_size], -0.1, 0.1))\n",
542 " b = tf.Variable(tf.zeros([vocabulary_size]))\n",
[all …]
|
| D | 5_word2vec.ipynb | 249 "vocabulary_size = 50000\n",
253 " count.extend(collections.Counter(words).most_common(vocabulary_size - 1))\n",
434 " tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))\n",
436 " tf.truncated_normal([vocabulary_size, embedding_size],\n",
438 " softmax_biases = tf.Variable(tf.zeros([vocabulary_size]))\n",
446 … labels=train_labels, num_sampled=num_sampled, num_classes=vocabulary_size))\n",
|
| /external/tensorflow/tensorflow/tools/api/golden/ |
| D | tensorflow.keras.preprocessing.sequence.pbtxt | 13 …argspec: "args=[\'sequence\', \'vocabulary_size\', \'window_size\', \'negative_samples\', \'shuffl…
|
| D | tensorflow.feature_column.pbtxt | 17 …argspec: "args=[\'key\', \'vocabulary_file\', \'vocabulary_size\', \'num_oov_buckets\', \'default_…
|
| /external/tensorflow/tensorflow/docs_src/tutorials/ |
| D | word2vec.md | 256 tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
266 tf.truncated_normal([vocabulary_size, embedding_size],
268 nce_biases = tf.Variable(tf.zeros([vocabulary_size]))
304 num_classes=vocabulary_size))
|
| D | recurrent.md | 148 # embedding_matrix is a tensor of shape [vocabulary_size, embedding size]
|
| /external/tensorflow/tensorflow/python/estimator/canned/ |
| D | dnn_testing_utils.py | 864 vocabulary_size=len(vocab_list)),
891 vocabulary_size=len(new_vocab_list)),
897 new_vocab_size=new_occupation.categorical_column.vocabulary_size,
900 old_vocab_size=occupation.categorical_column.vocabulary_size,
|
| D | linear_testing_utils.py | 1992 vocabulary_size=len(vocab_list))
2016 vocabulary_size=len(new_vocab_list))
2021 new_vocab_size=new_occupation.vocabulary_size,
2024 old_vocab_size=occupation.vocabulary_size,
|
| /external/tensorflow/tensorflow/docs_src/programmers_guide/ |
| D | embedding.md | 65 [vocabulary_size, embedding_size])
|
| /external/tensorflow/tensorflow/docs_src/get_started/ |
| D | feature_columns.md | 264 vocabulary_size=3)
|