Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
S
seminar-breakout
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Analytics
Analytics
CI / CD
Repository
Value Stream
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Shashank Suhas
seminar-breakout
Commits
709f89a9
Commit
709f89a9
authored
Dec 29, 2017
by
Yuxin Wu
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
fix old usage of leakyrelu
parent
81d5fbd8
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
tensorpack/models/nonlin.py
tensorpack/models/nonlin.py
+2
-2
No files found.
tensorpack/models/nonlin.py
View file @
709f89a9
...
...
@@ -7,7 +7,7 @@ import tensorflow as tf
from
.common
import
layer_register
,
VariableHolder
from
.batch_norm
import
BatchNorm
from
..utils.develop
import
deprecated
from
..utils.develop
import
log_
deprecated
__all__
=
[
'Maxout'
,
'PReLU'
,
'LeakyReLU'
,
'BNReLU'
]
...
...
@@ -62,7 +62,6 @@ def PReLU(x, init=0.001, name='output'):
@
layer_register
(
use_scope
=
None
)
@
deprecated
(
"Use tf.nn.leaky_relu in TF 1.4 instead!"
,
"2018-03-30"
)
def
LeakyReLU
(
x
,
alpha
,
name
=
'output'
):
"""
Leaky ReLU as in paper `Rectifier Nonlinearities Improve Neural Network Acoustic
...
...
@@ -73,6 +72,7 @@ def LeakyReLU(x, alpha, name='output'):
x (tf.Tensor): input
alpha (float): the slope.
"""
log_deprecated
(
"LeakyReLU"
,
"Use tf.nn.leaky_relu in TF 1.4 instead!"
,
"2018-03-30"
)
return
tf
.
maximum
(
x
,
alpha
*
x
,
name
=
name
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment