This resembles to the babl issue we are having. Is it possible that this is hardware related?
Tests fail with:
--8<---------------cut here---------------start------------->8---
=================================== FAILURES ===================================
__________________________________ test_selu ___________________________________
def test_selu():
x = K.placeholder(ndim=2)
f = K.function([x], [activations.selu(x)])
alpha = 1.6732632423543772848170429916717
scale = 1.0507009873554804934193349852946
positive_values = get_standard_values()
result = f([positive_values])[0]
assert_allclose(result, positive_values * scale, rtol=1e-05)
negative_values = np.array([[-1, -2]], dtype=K.floatx())
result = f([negative_values])[0]
true_result = (np.exp(negative_values) - 1) * scale * alpha
> assert_allclose(result, true_result)
E AssertionError:
E Not equal to tolerance rtol=1e-07, atol=0
E
E Mismatch: 50%
E Max absolute difference: 1.1920929e-07
E Max relative difference: 1.0726715e-07
E x: array([[-1.111331, -1.520167]], dtype=float32)
E y: array([[-1.111331, -1.520167]], dtype=float32)
tests/keras/activations_test.py:226: AssertionError
--8<---------------cut here---------------end--------------->8---
See attached log.
--
Pierre Neidhardt
https://ambrevar.xyz/