Skip to content

New pull request -- much cleaner #327

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
fchollet merged 7 commits into from
Jul 3, 2015
Merged

New pull request -- much cleaner #327

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
a808ae6
Add a test for the max-norm constraint
phreeza Jun 29, 2015
b48e39a
Add a test for the identity, non-negative, and unit-norm constraints
phreeza Jun 29, 2015
4956ed9
small PEP-8 changes
phreeza Jun 30, 2015
d59f251
make some texts a bit more explicit
phreeza Jun 30, 2015
f184db8
add exotic inputs to identity test
phreeza Jun 30, 2015
514ac06
missing axis parameter
phreeza Jun 30, 2015
acef252
change constraints tests to new constraint api
phreeza Jul 2, 2015
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
Prev Previous commit
Next Next commit
Add a test for the identity, non-negative, and unit-norm constraints
  • Loading branch information
@phreeza @tleeuwenburg
phreeza authored and tleeuwenburg committed Jul 3, 2015
commit b48e39aafd9ef413216444a6bfb97e867aa40e1c
20 changes: 20 additions & 0 deletions tests/auto/keras/test_constraints.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,5 +16,25 @@ def test_maxnorm(self):
normed = norm_instance(self.example_array)
assert(np.all(normed.eval() < m))

def test_nonneg(self):
from keras.constraints import nonneg

normed = nonneg(self.example_array)
assert(np.all(np.min(normed.eval(),axis=1) == 0.))

def test_identity(self):
from keras.constraints import identity

normed = identity(self.example_array)
assert(np.all(normed == self.example_array))

def test_unitnorm(self):
from keras.constraints import unitnorm

normed = unitnorm(self.example_array)
self.assertAlmostEqual(
np.max(np.abs(np.sqrt(np.sum(normed.eval()**2,axis=1))-1.))
,0.)

if __name__ == '__main__':
unittest.main()