This resembles to the babl issue we are having. Is it possible that this is
hardware related?

Pierre Neidhardt <mail@ambrevar.xyz> ezt írta (időpont: 2020. febr. 11., Ke
16:19):

> 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/
>