diff options
| author |  A. Unique TensorFlower <gardener@tensorflow.org> | 2016-11-21 13:05:02 -0800 |
|---|---|---|
| committer | TensorFlower Gardener <gardener@tensorflow.org> | 2016-11-21 13:25:03 -0800 |
| commit | 73d11f4ecbcf21fc799a35fd83f6678b2928fe17 (patch) | |
| tree | a7a751d897fe5181ff25d84b37897bc73a8eae28 /tensorflow/contrib/crf | |
| parent | 89fa351dabcc8756632d9b0828fb32e8e72ddc26 (diff) | |
Deprecate tf.batch_matmul and replace with equivalent calls to tf.matmul that now supports adjoint and batch matmul.
CL created by:
replace_string \
batch_matmul\\\( \
matmul\(
plus some manual edits, mostly s/adj_x/adjoint_a/ s/adj_y/adjoint_b/.
Change: 139821372
Diffstat (limited to 'tensorflow/contrib/crf')
| -rw-r--r-- | tensorflow/contrib/crf/README.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tensorflow/contrib/crf/README.md b/tensorflow/contrib/crf/README.md index c5458a23e9..a184e321bb 100644 --- a/tensorflow/contrib/crf/README.md +++ b/tensorflow/contrib/crf/README.md @@ -37,7 +37,7 @@ with tf.Graph().as_default(): # Compute unary scores from a linear layer. weights = tf.get_variable("weights", [num_features, num_tags]) matricized_x_t = tf.reshape(x_t, [-1, num_features]) - matricized_unary_scores = tf.batch_matmul(matricized_x_t, weights) + matricized_unary_scores = tf.matmul(matricized_x_t, weights) unary_scores = tf.reshape(matricized_unary_scores, [num_examples, num_words, num_tags]) |