keras-js/notebooks/activations.ipynb

In [2]:

import numpy as np
from keras import activations
from keras import backend as K

Using TensorFlow backend.

In [3]:

def format_decimal(arr):
    return [round(x * 1e6) / 1e6 for x in arr]

softmax

[activations.softmax.0] 1D

In [12]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softmax(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (6,)
out: [0.067194, 0.082071, 0.110784, 0.0608, 0.182652, 0.4965]

[activations.softmax.1] 2D

In [14]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 6)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softmax(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
in shape: (2, 6)
out shape: (2, 6)
out: [0.067194, 0.082071, 0.110784, 0.0608, 0.182652, 0.4965, 0.107768, 0.149902, 0.11105, 0.247147, 0.082268, 0.301865]

[activations.softmax.2] 1D

In [4]:

data_in = [0, 0.2, 0.5, -0.1, 1, 90]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softmax(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 90]
in shape: (6,)
out shape: (6,)
out: [0.0, 0.0, 0.0, 0.0, 0.0, 1.0]

softplus

[activations.softplus.0] 1D

In [25]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softplus(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (6,)
out: [0.693147, 0.798139, 0.974077, 0.644397, 1.313262, 2.126928]

[activations.softplus.1] 2D

In [26]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 6)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softplus(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
in shape: (2, 6)
out shape: (2, 6)
out: [0.693147, 0.798139, 0.974077, 0.644397, 1.313262, 2.126928, 0.67826, 0.854355, 0.693147, 1.171101, 0.554355, 1.313262]

[activations.softplus.2] 3D

In [27]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softplus(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.693147, 0.798139, 0.474077, 0.644397, 1.313262, 2.126928, 0.67826, 2.395545, 0.693147, 1.171101, 0.554355, 1.313262]

softsign

[activations.softsign.0] 1D

In [28]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softsign(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (6,)
out: [0.0, 0.166667, 0.333333, -0.090909, 0.5, 0.666667]

[activations.softsign.1] 2D

In [29]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 6)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softsign(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
in shape: (2, 6)
out shape: (2, 6)
out: [0.0, 0.166667, 0.333333, -0.090909, 0.5, 0.666667, -0.029126, 0.230769, 0.0, 0.444444, -0.230769, 0.5]

[activations.softsign.2] 3D

In [30]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.softsign(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.0, 0.166667, -0.333333, -0.090909, 0.5, 0.666667, -0.029126, 0.69697, 0.0, 0.444444, -0.230769, 0.5]

ReLU

[activations.relu.0] 1D

In [16]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.relu(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (6,)
out: [0.0, 0.2, 0.5, 0.0, 1.0, 2.0]

[activations.relu.1] 2D

In [17]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 6)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.relu(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
in shape: (2, 6)
out shape: (2, 6)
out: [0.0, 0.2, 0.5, 0.0, 1.0, 2.0, 0.0, 0.3, 0.0, 0.8, 0.0, 1.0]

[activations.relu.2] 3D

In [18]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.relu(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.0, 0.2, 0.0, 0.0, 1.0, 2.0, 0.0, 2.3, 0.0, 0.8, 0.0, 1.0]

[activations.relu.3] 3D, max_value=0.5

In [19]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.relu(K.variable(np.array([arr_in])), max_value=0.5)

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.0, 0.2, 0.0, 0.0, 0.5, 0.5, 0.0, 0.5, 0.0, 0.5, 0.0, 0.5]

[activations.relu.4] 3D, alpha=0.3

In [20]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.relu(K.variable(np.array([arr_in])), alpha=0.3)

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.0, 0.2, -0.15, -0.03, 1.0, 2.0, -0.009, 2.3, 0.0, 0.8, -0.09, 1.0]

tanh

[activations.tanh.0] 1D

In [22]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.tanh(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (6,)
out: [0.0, 0.197375, 0.462117, -0.099668, 0.761594, 0.964028]

[activations.tanh.1] 2D

In [23]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 6)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.tanh(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
in shape: (2, 6)
out shape: (2, 6)
out: [0.0, 0.197375, 0.462117, -0.099668, 0.761594, 0.964028, -0.029991, 0.291313, 0.0, 0.664037, -0.291313, 0.761594]

[activations.tanh.2] 3D

In [24]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.tanh(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.0, 0.197375, -0.462117, -0.099668, 0.761594, 0.964028, -0.029991, 0.980096, 0.0, 0.664037, -0.291313, 0.761594]

sigmoid

[activations.sigmoid.0] 1D

In [31]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.sigmoid(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (6,)
out: [0.5, 0.549834, 0.622459, 0.475021, 0.731059, 0.880797]

[activations.sigmoid.1] 2D

In [32]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 6)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.sigmoid(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
in shape: (2, 6)
out shape: (2, 6)
out: [0.5, 0.549834, 0.622459, 0.475021, 0.731059, 0.880797, 0.492501, 0.574443, 0.5, 0.689974, 0.425557, 0.731059]

[activations.sigmoid.2] 3D

In [33]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.sigmoid(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.5, 0.549834, 0.377541, 0.475021, 0.731059, 0.880797, 0.492501, 0.908877, 0.5, 0.689974, 0.425557, 0.731059]

hardSigmoid

[activations.hardSigmoid.0] 1D

In [35]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.hard_sigmoid(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (6,)
out: [0.5, 0.54, 0.6, 0.48, 0.7, 0.9]

[activations.hardSigmoid.1] 2D

In [36]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 6)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.hard_sigmoid(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
in shape: (2, 6)
out shape: (2, 6)
out: [0.5, 0.54, 0.6, 0.48, 0.7, 0.9, 0.494, 0.56, 0.5, 0.66, 0.44, 0.7]

[activations.hardSigmoid.2] 3D

In [37]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.hard_sigmoid(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.5, 0.54, 0.4, 0.48, 0.7, 0.9, 0.494, 0.96, 0.5, 0.66, 0.44, 0.7]

linear

[activations.linear.0] 1D

In [38]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2]
data_in_shape = (6,)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.linear(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (6,)
out: [0.0, 0.2, 0.5, -0.1, 1.0, 2.0]

[activations.linear.1] 2D

In [39]:

data_in = [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 6)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.linear(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, 0.5, -0.1, 1, 2, -0.03, 0.3, 0, 0.8, -0.3, 1]
in shape: (2, 6)
out shape: (2, 6)
out: [0.0, 0.2, 0.5, -0.1, 1.0, 2.0, -0.03, 0.3, 0.0, 0.8, -0.3, 1.0]

[activations.linear.2] 3D

In [40]:

data_in = [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
data_in_shape = (2, 2, 3)
print('in:', data_in)
print('in shape:', data_in_shape)
arr_in = np.array(data_in, dtype='float32').reshape(data_in_shape)

result = activations.linear(K.variable(np.array([arr_in])))

arr_out = K.eval(result)[0]
print('out shape:', arr_out.shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

in: [0, 0.2, -0.5, -0.1, 1, 2, -0.03, 2.3, 0, 0.8, -0.3, 1]
in shape: (2, 2, 3)
out shape: (2, 2, 3)
out: [0.0, 0.2, -0.5, -0.1, 1.0, 2.0, -0.03, 2.3, 0.0, 0.8, -0.3, 1.0]

In [ ]: