aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/contrib/slim
diff options
context:
space:
mode:
authorGravatar Sourabh Bajaj <sourabhbajaj@google.com>2017-11-30 16:37:11 -0800
committerGravatar TensorFlower Gardener <gardener@tensorflow.org>2017-11-30 16:41:01 -0800
commitb2db981a6731e978453862a73dab892bc674db68 (patch)
treec11a7c4038e2595268113c2859c1d0d3072ede4f /tensorflow/contrib/slim
parent0438ac79bdb503ed267bec2146e7136ac8e99ff9 (diff)
Merge changes from github.
PiperOrigin-RevId: 177526301
Diffstat (limited to 'tensorflow/contrib/slim')
-rw-r--r--tensorflow/contrib/slim/README.md9
-rw-r--r--tensorflow/contrib/slim/python/slim/evaluation.py4
2 files changed, 8 insertions, 5 deletions
diff --git a/tensorflow/contrib/slim/README.md b/tensorflow/contrib/slim/README.md
index f7a85557ca..dc92ae0c85 100644
--- a/tensorflow/contrib/slim/README.md
+++ b/tensorflow/contrib/slim/README.md
@@ -441,7 +441,8 @@ module. Consider the simple case where we want to train the VGG network:
```python
import tensorflow as tf
-vgg = tf.contrib.slim.nets.vgg
+import tensorflow.contrib.slim.nets as nets
+vgg = nets.vgg
# Load the images and labels.
images, labels = ...
@@ -559,9 +560,10 @@ examine the following sample of training the VGG network:
```python
import tensorflow as tf
+import tensorflow.contrib.slim.nets as nets
slim = tf.contrib.slim
-vgg = tf.contrib.slim.nets.vgg
+vgg = nets.vgg
...
@@ -809,9 +811,10 @@ Putting it all together:
```python
import tensorflow as tf
+import tensorflow.contrib.slim.nets as nets
slim = tf.contrib.slim
-vgg = tf.contrib.slim.nets.vgg
+vgg = nets.vgg
# Load the data
diff --git a/tensorflow/contrib/slim/python/slim/evaluation.py b/tensorflow/contrib/slim/python/slim/evaluation.py
index cdb720b36b..3caf4e02da 100644
--- a/tensorflow/contrib/slim/python/slim/evaluation.py
+++ b/tensorflow/contrib/slim/python/slim/evaluation.py
@@ -34,7 +34,7 @@ the metrics and finally call the `evaluation` method:
"mse": slim.metrics.mean_squared_error(predictions, labels),
})
- inital_op = tf.group(
+ initial_op = tf.group(
tf.global_variables_initializer(),
tf.local_variables_initializer())
@@ -42,7 +42,7 @@ the metrics and finally call the `evaluation` method:
metric_values = slim.evaluation(
sess,
num_evals=1,
- inital_op=initial_op,
+ initial_op=initial_op,
eval_op=names_to_updates.values(),
final_op=name_to_values.values())