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

Added init_seed parameter in Functional make initialized weights and training results reproducible #57

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Added init_seed parameter in Functional make initialized weights and training results reproducible #57

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 6 additions & 1 deletion sciann/functionals/functional.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,9 @@
trainable: Boolean.
False if network is not trainable, True otherwise.
Default value is True.
init_seed: int.
To make weights initialization reproducible.
Default value is True.

# Raises
ValueError:
Expand All @@ -74,6 +77,7 @@ def Functional(
kernel_regularizer=None,
bias_regularizer=None,
trainable=True,
init_seed=None,
**kwargs):
# prepare hidden layers.
if hidden_layers is None:
Expand All @@ -85,7 +89,8 @@ def Functional(
# prepare kernel initializers.
activations, def_biasinit, def_kerinit = \
prepare_default_activations_and_initializers(
len(hidden_layers) * [activation] + [output_activation]
len(hidden_layers) * [activation] + [output_activation],
seed=init_seed
)
if kernel_initializer is None:
kernel_initializer = def_kerinit
Expand Down
2 changes: 2 additions & 0 deletions sciann/utils/utilities.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
from __future__ import print_function

import os
import random
import numpy as np
from numpy import pi

Expand Down Expand Up @@ -49,6 +50,7 @@ def set_random_seed(val=1234):
val: A seed value..

"""
random.seed(val)
np.random.seed(val)
if _is_tf_1():
tf.set_random_seed(val)
Expand Down