Fix typos

tensorflow/compiler/tests/ftrl_test.py

@@ -218,7 +218,7 @@ class FtrlOptimizerTest(XLATestCase):
         self.assertAllClose(np.array([-0.24059935, -0.46829352]), var0.eval())
         self.assertAllClose(np.array([-0.02406147, -0.04830509]), var1.eval())
 
-  # When variables are intialized with Zero, FTRL-Proximal has two properties:
+  # When variables are initialized with Zero, FTRL-Proximal has two properties:
   # 1. Without L1&L2 but with fixed learning rate, FTRL-Proximal is identical
   # with GradientDescent.
   # 2. Without L1&L2 but with adaptive learning rate, FTRL-Proximal is idential

tensorflow/compiler/xla/xla_data.proto

@@ -200,7 +200,7 @@ message OpMetadata {
   string op_name = 2;
   // Indicate a file and line that this op is associated to in a user's program.
   //
-  // e.g. it could be be the file and line of user code that generated the op.
+  // e.g. it could be the file and line of user code that generated the op.
   string source_file = 3;
   int32 source_line = 4;
 }

tensorflow/contrib/distributions/python/ops/relaxed_bernoulli.py

@@ -52,7 +52,7 @@ class RelaxedBernoulli(transformed_distribution.TransformedDistribution):
   the RelaxedBernoulli can suffer from underflow issues. In many case loss
   functions such as these are invariant under invertible transformations of
   the random variables. The KL divergence, found in the variational autoencoder
-  loss, is an example. Because RelaxedBernoullis are sampled by by a Logistic
+  loss, is an example. Because RelaxedBernoullis are sampled by a Logistic
   random variable followed by a `tf.sigmoid` op, one solution is to treat
   the Logistic as the random variable and `tf.sigmoid` as downstream. The
   KL divergences of two Logistics, which are always followed by a `tf.sigmoid`

tensorflow/contrib/distributions/python/ops/sample_stats.py

@@ -47,7 +47,7 @@ def percentile(x,
   """Compute the `q`-th percentile of `x`.
 
   Given a vector `x`, the `q`-th percentile of `x` is the value `q / 100` of the
-  way from the minimum to the maximum in in a sorted copy of `x`.
+  way from the minimum to the maximum in a sorted copy of `x`.
 
   The values and distances of the two nearest neighbors as well as the
   `interpolation` parameter will determine the percentile if the normalized

tensorflow/contrib/graph_editor/transform.py

@@ -446,7 +446,7 @@ class Transformer(object):
       # TODO(fkp): return a subgraph?
       op_, op_outputs_ = self.transform_op_handler(info, op)
       if op is op_:
-        raise ValueError("In-place tranformation not allowed.")
+        raise ValueError("In-place transformation not allowed.")
 
       # Process op.
       info.transformed_ops[op] = op_

tensorflow/contrib/training/python/training/evaluation.py

@@ -226,7 +226,7 @@ def checkpoints_iterator(checkpoint_dir,
 
   This behavior gives control to callers on what to do if checkpoints do not
   come fast enough or stop being generated.  For example, if callers have a way
-  to detect that the training has stopped and know that no new new checkpoints
+  to detect that the training has stopped and know that no new checkpoints
   will be generated, they can provide a `timeout_fn` that returns `True` when
   the training has stopped.  If they know that the training is still going on
   they return `False` instead.

tensorflow/core/lib/gtl/optional.h

@@ -656,7 +656,7 @@ class optional : private internal_optional::optional_data<T>,
   constexpr const T& reference() const { return *this->pointer(); }
   T& reference() { return *(this->pointer()); }
 
-  // T constaint checks.  You can't have an optional of nullopt_t, in_place_t or
+  // T constraint checks.  You can't have an optional of nullopt_t, in_place_t or
   // a reference.
   static_assert(
       !std::is_same<nullopt_t, typename std::remove_cv<T>::type>::value,

tensorflow/docs_src/api_guides/python/contrib.losses.md

@@ -13,8 +13,8 @@ of samples in the batch and `d1` ... `dN` are the remaining dimensions.
 It is common, when training with multiple loss functions, to adjust the relative
 strengths of individual losses. This is performed by rescaling the losses via
 a `weight` parameter passed to the loss functions. For example, if we were
-training with both log_loss and mean_square_error, and we wished that the
-log_loss penalty be twice as severe as the mean_square_error, we would
+training with both log_loss and mean_squared_error, and we wished that the
+log_loss penalty be twice as severe as the mean_squared_error, we would
 implement this as:
 
 ```python
@@ -22,7 +22,7 @@ implement this as:
   tf.contrib.losses.log(predictions, labels, weight=2.0)
 
   # Uses default weight of 1.0
-  tf.contrib.losses.mean_square_error(predictions, labels)
+  tf.contrib.losses.mean_squared_error(predictions, labels)
 
   # All the losses are collected into the `GraphKeys.LOSSES` collection.
   losses = tf.get_collection(tf.GraphKeys.LOSSES)
@@ -74,7 +74,7 @@ these predictions.
   predictions = MyModelPredictions(images)
 
   weight = tf.cast(tf.greater(depths, 0), tf.float32)
-  loss  = tf.contrib.losses.mean_square_error(predictions, depths, weight)
+  loss  = tf.contrib.losses.mean_squared_error(predictions, depths, weight)
 ```
 
 Note that when using weights for the losses, the final average is computed
@@ -100,7 +100,7 @@ weighted average over the individual prediction errors:
 
   weight = MyComplicatedWeightingFunction(labels)
   weight = tf.div(weight, tf.size(weight))
-  loss = tf.contrib.losses.mean_square_error(predictions, depths, weight)
+  loss = tf.contrib.losses.mean_squared_error(predictions, depths, weight)
 ```
 
 @{tf.contrib.losses.absolute_difference}

tensorflow/python/debug/cli/analyzer_cli.py

@@ -1312,7 +1312,7 @@ class DebugAnalyzer(object):
     all_inputs = copy.copy(tracker(node_name, is_control=False))
     is_ctrl = [False] * len(all_inputs)
     if include_control:
-      # Sort control inputs or recipients in in alphabetical order of the node
+      # Sort control inputs or recipients in alphabetical order of the node
       # names.
       ctrl_inputs = sorted(tracker(node_name, is_control=True))
       all_inputs.extend(ctrl_inputs)