Skip to content
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

Jump to bottom

Feat/orthoconv2d #51

Closed
wants to merge 25 commits into from
Closed

Feat/orthoconv2d #51

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
1ecec5f
spectral_norm_conv and test_normalizers
franckma31 Feb 10, 2022
27d1fcd
add PadConv2D layers and test
franckma31 Feb 13, 2022
dd2b81d
PadConv2D add support for kernel_size as integer + test with several…
franckma31 Feb 14, 2022
60db98c
Add OrthoConv2D layer with spectral_norm_conv within the graph, and L…
franckma31 Feb 15, 2022
b364f28
update _v initialization in spectral_norm with a tf.zeros since the f…
franckma31 Feb 15, 2022
1512f5b
Add regularizer.py with Lorth regul
franckma31 Feb 15, 2022
c776dbd
PEP-8 convention
franckma31 Feb 15, 2022
c07a013
change file name and add utils methods for Singular Values computatio…
franckma31 Feb 17, 2022
0737403
change file name and add utils methods for Singular Values computatio…
franckma31 Feb 17, 2022
282bb23
add support for k_lip_tolerance_factor in test_layers
franckma31 Feb 17, 2022
b85be94
change function name compute_layer_sv and clean
franckma31 Feb 17, 2022
a4abf3e
PEP-8 convention
franckma31 Feb 17, 2022
fa2fcaa
test compute_layers_sv for OrthoConv2D
franckma31 Feb 17, 2022
6546c3d
fix a test errors for tf2.8
franckma31 Feb 17, 2022
658da78
bug fixed in test error: internal_input_shape for compute_output_shape
franckma31 Feb 17, 2022
2703049
bug fix on FrobeniusConv2D::condense
franckma31 Feb 17, 2022
4c30dc4
FrobeniusConv2D vanilla_export bug correction + unit test
franckma31 Feb 28, 2022
b4ef238
modify _power_iteration_conv for padding='same' and strides
franckma31 Mar 11, 2022
3abbe0f
Correct _compute_lip_coef computation for spectralConv2D with strides…
franckma31 Mar 11, 2022
525da45
cleaning and naming convention
franckma31 Mar 11, 2022
3ded9d9
add unit test on strided convolutions
franckma31 Mar 11, 2022
e1aec2a
lint formatting
franckma31 Mar 13, 2022
dc7c036
compute_layer_sv.py: bug on compute_sv_add , and support for sequenti…
franckma31 Mar 29, 2022
6420318
orthoconv: changed camel case to snake case for attributes and methods
Apr 5, 2022
12d088a
orthoconv: added missing documentation
Apr 5, 2022
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
3 changes: 2 additions & 1 deletion deel/lip/activations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,9 +11,10 @@
from tensorflow.keras import backend as K
from tensorflow.keras.constraints import MinMaxNorm
from tensorflow.keras.layers import Layer, PReLU
from .layers import LipschitzLayer
from tensorflow.keras.utils import register_keras_serializable

from .layers import LipschitzLayer


@register_keras_serializable("deel-lip", "MaxMin")
class MaxMin(Layer, LipschitzLayer):
Expand Down
Loading