aboutsummaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorGravatar Reed Wanderman-Milne <reedwm@google.com>2018-06-19 12:08:24 -0700
committerGravatar TensorFlower Gardener <gardener@tensorflow.org>2018-06-19 12:12:44 -0700
commit8f19772410ec20010e9930f9765dbd3aaeb06111 (patch)
treee612fc7a9d1bdf22b4abf43dd454dd95b170c227
parentebe34a138382a873063e7472fc33ee33a2d6ae36 (diff)
Rollback documentation that I forgot to rollback last time.
PiperOrigin-RevId: 201218249
-rw-r--r--tensorflow/python/keras/engine/base_layer.py9
1 files changed, 0 insertions, 9 deletions
diff --git a/tensorflow/python/keras/engine/base_layer.py b/tensorflow/python/keras/engine/base_layer.py
index e8cdda30a2..4814275fd5 100644
--- a/tensorflow/python/keras/engine/base_layer.py
+++ b/tensorflow/python/keras/engine/base_layer.py
@@ -88,15 +88,6 @@ class Layer(checkpointable.CheckpointableBase):
once. Should actually perform the logic of applying the layer to the
input tensors (which should be passed in as the first argument).
- All floating point tensor inputs and arguments are casted to the layer's
- dtype, before the body of the layer computation happens. For models with
- layers of different dtypes, this helps getting rid of the explicit casts
- between layers.
-
- The casting behavior can be customized in subclasses by overridding
- `_cast_inputs_and_args()` function, which is useful if certain or all inputs
- should not be casted.
-
Arguments:
trainable: Boolean, whether the layer's variables should be trainable.
name: String name of the layer.