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
99a216bf
You need to sign in or sign up before continuing.
Commit
99a216bf
authored
Jan 01, 2017
by
Yuxin Wu
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
small fix on docs
parent
c3f5307e
Changes
5
Show whitespace changes
Inline
Side-by-side
Showing
5 changed files
with
7 additions
and
7 deletions
+7
-7
tensorpack/callbacks/param.py
tensorpack/callbacks/param.py
+1
-1
tensorpack/models/__init__.py
tensorpack/models/__init__.py
+2
-2
tensorpack/models/shapes.py
tensorpack/models/shapes.py
+2
-2
tensorpack/tfutils/varmanip.py
tensorpack/tfutils/varmanip.py
+1
-1
tensorpack/utils/logger.py
tensorpack/utils/logger.py
+1
-1
No files found.
tensorpack/callbacks/param.py
View file @
99a216bf
...
...
@@ -165,7 +165,7 @@ class ScheduledHyperParamSetter(HyperParamSetter):
def
__init__
(
self
,
param
,
schedule
,
interp
=
None
):
"""
:param schedule: [(epoch1, val1), (epoch2, val2), (epoch3, val3), ...]
(ep, val) means set the param to
`val`
after the `ep`th epoch.
(ep, val) means set the param to
"val"
after the `ep`th epoch.
If epoch == 0, the value is set before training.
:param interp: None: no interpolation. 'linear': linear interpolation
"""
...
...
tensorpack/models/__init__.py
View file @
99a216bf
...
...
@@ -27,8 +27,8 @@ for _, module_name, _ in walk_packages(
class
LinearWrap
(
object
):
""" A simple wrapper to easily create
linear
graph,
for layers with one input&output, or tf function with one input&output
""" A simple wrapper to easily create
"linear"
graph,
consisting of layers / symbolic functions with only one input & output.
"""
class
TFModuleFunc
(
object
):
...
...
tensorpack/models/shapes.py
View file @
99a216bf
...
...
@@ -14,8 +14,8 @@ def ConcatWith(x, dim, tensor):
A wrapper around `tf.concat` to support `LinearWrap`
:param x: the input tensor
:param dim: the dimension along which to concatenate
:param tensor: a tensor or list of tensor to concatenate with x.
x will be
at the beginning
:param tensor: a tensor or list of tensor to concatenate with x.
x will be
at the beginning
:return: tf.concat(dim, [x] + [tensor])
"""
if
type
(
tensor
)
!=
list
:
...
...
tensorpack/tfutils/varmanip.py
View file @
99a216bf
tensorpack/utils/logger.py
View file @
99a216bf
...
...
@@ -10,7 +10,7 @@ from datetime import datetime
from
six.moves
import
input
import
sys
__all__
=
[]
__all__
=
[
'set_logger_dir'
,
'disable_logger'
,
'auto_set_dir'
,
'warn_dependency'
]
class
_MyFormatter
(
logging
.
Formatter
):
def
format
(
self
,
record
):
...
...
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