diff options
| author |  A. Unique TensorFlower <gardener@tensorflow.org> | 2016-11-28 10:36:18 -0800 |
|---|---|---|
| committer | TensorFlower Gardener <gardener@tensorflow.org> | 2016-11-28 10:42:47 -0800 |
| commit | 17fe6574eb7929f92d081a754144747527af2a24 (patch) | |
| tree | e148ccd75eec33d1e801582a431551de214572d7 | |
| parent | a1dd79c1d8b7ad93f06074a29c6029e9cd9af6c4 (diff) | |
Add warning note to Variable.initialized_value documentation.
Change: 140374197
| -rw-r--r-- | tensorflow/python/ops/variables.py | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/tensorflow/python/ops/variables.py b/tensorflow/python/ops/variables.py index 40c90dfba8..9f3b55fc12 100644 --- a/tensorflow/python/ops/variables.py +++ b/tensorflow/python/ops/variables.py @@ -518,6 +518,10 @@ class Variable(object): You should use this instead of the variable itself to initialize another variable with a value that depends on the value of this variable. + Beware of using initialized_value except during initialization: + initialized_value causes the Variable's initializer op to be run, so running + this op resets the variable to the initial value. + ```python # Initialize 'v' with a random tensor. v = tf.Variable(tf.truncated_normal([10, 40])) |