Skip to content

[fix bug] copy original model's trainable_weights and nontrainable_weights when initializing ModelLayer #1026

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
warshallrho merged 10 commits into from
Jul 21, 2019
Merged

[fix bug] copy original model's trainable_weights and nontrainable_weights when initializing ModelLayer #1026

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
3cc91b2
add allow_pickle=True in np.load()
warshallrho Jul 16, 2019
d8ca42f
Merge branch 'master' into master
warshallrho Jul 16, 2019
a14d279
Update CHANGELOG.md
warshallrho Jul 16, 2019
54b161b
Merge branch 'master' of https://github.com/warshallrho/tensorlayer2
warshallrho Jul 16, 2019
5cd0cf8
yapf
warshallrho Jul 16, 2019
715cb05
yapf
warshallrho Jul 16, 2019
c064ee0
yapf
warshallrho Jul 16, 2019
b565b47
Merge branch 'master' of https://github.com/tensorlayer/tensorlayer
warshallrho Jul 20, 2019
bad3a22
[fix bug] copy original model's trainable_weights and nontrainable_we…
warshallrho Jul 20, 2019
a8c352f
Update CHANGELOG.md
warshallrho Jul 20, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,9 +106,10 @@ To release a new version, please update the changelog as followed:

### Fixed
- Fix `tf.models.Model._construct_graph` for list of outputs, e.g. STN case (PR #1010)
- Enable better `in_channels` exception raise. (pR #1015)
- Enable better `in_channels` exception raise. (PR #1015)
- Set allow_pickle=True in np.load() (#PR 1021)
- Remove `private_method` decorator (#PR 1025)
- Copy original model's `trainable_weights` and `nontrainable_weights` when initializing `ModelLayer` (#PR 1026)

### Removed

Expand All @@ -118,7 +119,7 @@ To release a new version, please update the changelog as followed:

- @zsdonghao
- @ChrisWu1997: #1010 #1015 #1025
- @warshallrho: #1017 #1021
- @warshallrho: #1017 #1021 #1026
- @ArnoldLIULJ: #1023
- @JingqingZ: #1023

Expand Down
2 changes: 2 additions & 0 deletions tensorlayer/layers/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -512,6 +512,8 @@ def __init__(self, model, name=None):

# Layer weight state
self._all_weights = model.all_weights
self._trainable_weights = model.trainable_weights
self._nontrainable_weights = model.nontrainable_weights

# Layer training state
self.is_train = True
Expand Down