def Selu(self, x):
'''Composes Keras' implementation for SELU Activation Function
Arguments:
x (tensor):
Input tensor
Returns:
Tensor, output of 'SELU' activatin function
'''
return selu(x)
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())
# cntk can't rebind the input shape, so create the model again to test different batch size
if (K.backend() == 'cntk'):
x2 = K.placeholder(ndim=2)
f = K.function([x2], [activations.selu(x2)])
result = f([negative_values])[0]
true_result = (np.exp(negative_values) - 1) * scale * alpha
assert_allclose(result, true_result)
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())
# cntk can't rebind the input shape, so create the model again to
# test different batch size
if (K.backend() == 'cntk'):
x2 = K.placeholder(ndim=2)
f = K.function([x2], [activations.selu(x2)])
result = f([negative_values])[0]
true_result = (np.exp(negative_values) - 1) * scale * alpha
assert_allclose(result, true_result)
def test_selu(self):
x = backend.placeholder(ndim=2)
f = backend.function([x], [activations.selu(x)])
alpha = 1.6732632423543772848170429916717
scale = 1.0507009873554804934193349852946
positive_values = np.array([[1, 2]], dtype=backend.floatx())
result = f([positive_values])[0]
self.assertAllClose(result, positive_values * scale, rtol=1e-05)
negative_values = np.array([[-1, -2]], dtype=backend.floatx())
result = f([negative_values])[0]
true_result = (np.exp(negative_values) - 1) * scale * alpha
self.assertAllClose(result, true_result)
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)
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)
def call(self, x):
return K.concatenate((selu(x), selu(-x)), -1)
'celu':
Lambda(lambda x: tf.nn.crelu(x) * 1.270926833152771),
'elu':
Lambda(lambda x: elu(x) * 1.2716004848480225),
'gelu':
Lambda(lambda x: gelu(x) * 1.7015043497085571),
# 'glu': lambda x: jax.nn.glu(x) * 1.8484294414520264,
'leaky_relu':
Lambda(lambda x: tf.nn.leaky_relu(x) * 1.70590341091156),
'log_sigmoid':
Lambda(lambda x: tf.math.log(tf.nn.sigmoid(x)) * 1.9193484783172607),
'log_softmax':
Lambda(lambda x: tf.math.log(tf.nn.softmax(x)) * 1.0002083778381348),
'relu':
Lambda(lambda x: relu(x) * 1.7139588594436646),
'relu6':
Lambda(lambda x: tf.nn.relu6(x) * 1.7131484746932983),
'selu':
Lambda(lambda x: selu(x) * 1.0008515119552612),
'sigmoid':
Lambda(lambda x: sigmoid(x) * 4.803835391998291),
'silu':
Lambda(lambda x: tf.nn.silu(x) * 1.7881293296813965),
'soft_sign':
Lambda(lambda x: tf.nn.softsign(x) * 2.338853120803833),
'softplus':
Lambda(lambda x: softplus(x) * 1.9203323125839233),
'tanh':
Lambda(lambda x: tanh(x) * 1.5939117670059204),
}
