keras-js/notebooks/core/Dense.ipynb

In [2]:

import numpy as np
from keras.models import Model
from keras.layers import Input
from keras.layers.core import Dense
from keras import backend as K

Using TensorFlow backend.

In [3]:

def format_decimal(arr, places=6):
    return [round(x * 10**places) / 10**places for x in arr]

Dense

[core.Dense.0] test 1

In [3]:

layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='linear')(layer_0)
model = Model(input=layer_0, output=layer_1)

W = np.array([0.1, 0.4, 0.5, 0.1, 1, -2, 0, 0.3, 0.2, 0.1, 3, 0]).reshape((6, 2))
b = np.array([0.5, 0.7])
model.set_weights([W, b])

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 = model.predict(np.array([arr_in]))
arr_out = 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: (2,)
out: [7.3, -0.21]

[core.Dense.1] test 2 (with sigmoid activation)

In [4]:

layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='sigmoid')(layer_0)
model = Model(input=layer_0, output=layer_1)

W = np.array([0.1, 0.4, 0.5, 0.1, 1, -2, 0, 0.3, 0.2, 0.1, 3, 0]).reshape((6, 2))
b = np.array([0.5, 0.7])
model.set_weights([W, b])

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 = model.predict(np.array([arr_in]))
arr_out = 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: (2,)
out: [0.999325, 0.447692]

[core.Dense.2] test 3 (with softplus activation and no bias)

In [5]:

layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='softplus', bias=False)(layer_0)
model = Model(input=layer_0, output=layer_1)

W = np.array([0.1, 0.4, 0.5, 0.1, 1, -2, 0, 0.3, 0.2, 0.1, 3, 0]).reshape((6, 2))
model.set_weights([W])

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 = model.predict(np.array([arr_in]))
arr_out = 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: (2,)
out: [6.801113, 0.338274]

[core.Dense.3] [GPU] test 1

In [3]:

layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='linear')(layer_0)
model = Model(input=layer_0, output=layer_1)

W = np.array([0.1, 0.4, 0.5, 0.1, 1, -2, 0, 0.3, 0.2, 0.1, 3, 0]).reshape((6, 2))
b = np.array([0.5, 0.7])
model.set_weights([W, b])

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 = model.predict(np.array([arr_in]))
arr_out = 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: (2,)
out: [7.3, -0.21]

[core.Dense.4] [GPU] test 2 (with sigmoid activation)

In [4]:

layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='sigmoid')(layer_0)
model = Model(input=layer_0, output=layer_1)

W = np.array([0.1, 0.4, 0.5, 0.1, 1, -2, 0, 0.3, 0.2, 0.1, 3, 0]).reshape((6, 2))
b = np.array([0.5, 0.7])
model.set_weights([W, b])

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 = model.predict(np.array([arr_in]))
arr_out = 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: (2,)
out: [0.999325, 0.447692]

[core.Dense.5] [GPU] test 3 (with softplus activation and no bias)

In [5]:

layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='softplus', bias=False)(layer_0)
model = Model(input=layer_0, output=layer_1)

W = np.array([0.1, 0.4, 0.5, 0.1, 1, -2, 0, 0.3, 0.2, 0.1, 3, 0]).reshape((6, 2))
model.set_weights([W])

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 = model.predict(np.array([arr_in]))
arr_out = 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: (2,)
out: [6.801113, 0.338274]

In [ ]: