aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/contrib/quantize/python/quantize_graph.py
diff options
context:
space:
mode:
Diffstat (limited to 'tensorflow/contrib/quantize/python/quantize_graph.py')
-rw-r--r--tensorflow/contrib/quantize/python/quantize_graph.py2
1 files changed, 1 insertions, 1 deletions
diff --git a/tensorflow/contrib/quantize/python/quantize_graph.py b/tensorflow/contrib/quantize/python/quantize_graph.py
index d0fb55da74..0b74b438ac 100644
--- a/tensorflow/contrib/quantize/python/quantize_graph.py
+++ b/tensorflow/contrib/quantize/python/quantize_graph.py
@@ -155,7 +155,7 @@ def experimental_create_training_graph(input_graph=None,
often fail.
Args:
- input_graph: The tf.Graph to be transformed,if None then defaults to the
+ input_graph: The tf.Graph to be transformed, if None then defaults to the
default graph.
weight_bits: Number of bits to use for quantizing weights.
activation_bits: Number of bits to use for quantizing activations.