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
17cb3554
Commit
17cb3554
authored
Oct 06, 2019
by
Yuxin Wu
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update docs
parent
e83b0797
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
4 additions
and
1 deletion
+4
-1
docs/tutorial/save-load.md
docs/tutorial/save-load.md
+4
-1
No files found.
docs/tutorial/save-load.md
View file @
17cb3554
...
...
@@ -51,7 +51,7 @@ is in fact a small helper which uses some heuristics to return you one of
[
DictRestore
](
../modules/tfutils.html#tensorpack.tfutils.sessinit.DictRestore
)
.
They are responsible for the actual initialization work.
Whatever you use in
`session_init`
, this is what happens during the
loading
:
Whatever you use in
`session_init`
, this is what happens during the
initialization
:
*
Variable restoring is completely based on __exact name match__ between
variables in the current graph and variables in the
`session_init`
initializer.
...
...
@@ -59,6 +59,9 @@ Whatever you use in `session_init`, this is what happens during the loading:
*
Variables of the same name but incompatible shapes will cause exceptions.
If you set
`ignore_mismatch=True`
, then such errors will only be printed as warnings.
You can also use
`SmartInit`
to load a model to a session manually,
without involving the rest of the tensorpack, by
`SmartInit(...).init(session)`
.
## Transfer Learning
Therefore, transfer learning is trivial.
...
...
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