notebook.community

Edit and run 





In [1]:



    


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
import json
from collections import OrderedDict



    


















    






Using TensorFlow backend.

















In [2]:



    


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



    











In [3]:



    


DATA = OrderedDict()

Dense

[core.Dense.0] test 1





In [4]:



    


layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='linear')(layer_0)
model = Model(inputs=layer_0, outputs=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]
data_out_shape = arr_out.shape
print('out shape:', data_out_shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

DATA['core.Dense.0'] = {
    'input': {'data': data_in, 'shape': data_in_shape},
    'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in [W, b]],
    'expected': {'data': data_out, 'shape': data_out_shape}
}



    


















    






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 [5]:



    


layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='sigmoid')(layer_0)
model = Model(inputs=layer_0, outputs=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]
data_out_shape = arr_out.shape
print('out shape:', data_out_shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

DATA['core.Dense.1'] = {
    'input': {'data': data_in, 'shape': data_in_shape},
    'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in [W, b]],
    'expected': {'data': data_out, 'shape': data_out_shape}
}



    


















    






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 [6]:



    


layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='softplus', use_bias=False)(layer_0)
model = Model(inputs=layer_0, outputs=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]
data_out_shape = arr_out.shape
print('out shape:', data_out_shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

DATA['core.Dense.2'] = {
    'input': {'data': data_in, 'shape': data_in_shape},
    'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in [W]],
    'expected': {'data': data_out, 'shape': data_out_shape}
}



    


















    






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 [7]:



    


layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='linear')(layer_0)
model = Model(inputs=layer_0, outputs=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]
data_out_shape = arr_out.shape
print('out shape:', data_out_shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

DATA['core.Dense.3'] = {
    'input': {'data': data_in, 'shape': data_in_shape},
    'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in [W, b]],
    'expected': {'data': data_out, 'shape': data_out_shape}
}



    


















    






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 [8]:



    


layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='sigmoid')(layer_0)
model = Model(inputs=layer_0, outputs=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]
data_out_shape = arr_out.shape
print('out shape:', data_out_shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

DATA['core.Dense.4'] = {
    'input': {'data': data_in, 'shape': data_in_shape},
    'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in [W, b]],
    'expected': {'data': data_out, 'shape': data_out_shape}
}



    


















    






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 [9]:



    


layer_0 = Input(shape=(6,))
layer_1 = Dense(2, activation='softplus', use_bias=False)(layer_0)
model = Model(inputs=layer_0, outputs=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]
data_out_shape = arr_out.shape
print('out shape:', data_out_shape)
data_out = format_decimal(arr_out.ravel().tolist())
print('out:', data_out)

DATA['core.Dense.5'] = {
    'input': {'data': data_in, 'shape': data_in_shape},
    'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in [W]],
    'expected': {'data': data_out, 'shape': data_out_shape}
}



    


















    






in: [0, 0.2, 0.5, -0.1, 1, 2]
in shape: (6,)
out shape: (2,)
out: [6.801113, 0.338274]

export for Keras.js tests





In [10]:



    


json.dumps(DATA)



    


















    
Out[10]:








'{"core.Dense.0": {"expected": {"data": [7.3, -0.21], "shape": [2]}, "input": {"data": [0, 0.2, 0.5, -0.1, 1, 2], "shape": [6]}, "weights": [{"data": [0.1, 0.4, 0.5, 0.1, 1.0, -2.0, 0.0, 0.3, 0.2, 0.1, 3.0, 0.0], "shape": [6, 2]}, {"data": [0.5, 0.7], "shape": [2]}]}, "core.Dense.1": {"expected": {"data": [0.999325, 0.447692], "shape": [2]}, "input": {"data": [0, 0.2, 0.5, -0.1, 1, 2], "shape": [6]}, "weights": [{"data": [0.1, 0.4, 0.5, 0.1, 1.0, -2.0, 0.0, 0.3, 0.2, 0.1, 3.0, 0.0], "shape": [6, 2]}, {"data": [0.5, 0.7], "shape": [2]}]}, "core.Dense.2": {"expected": {"data": [6.801113, 0.338274], "shape": [2]}, "input": {"data": [0, 0.2, 0.5, -0.1, 1, 2], "shape": [6]}, "weights": [{"data": [0.1, 0.4, 0.5, 0.1, 1.0, -2.0, 0.0, 0.3, 0.2, 0.1, 3.0, 0.0], "shape": [6, 2]}]}, "core.Dense.3": {"expected": {"data": [7.3, -0.21], "shape": [2]}, "input": {"data": [0, 0.2, 0.5, -0.1, 1, 2], "shape": [6]}, "weights": [{"data": [0.1, 0.4, 0.5, 0.1, 1.0, -2.0, 0.0, 0.3, 0.2, 0.1, 3.0, 0.0], "shape": [6, 2]}, {"data": [0.5, 0.7], "shape": [2]}]}, "core.Dense.4": {"expected": {"data": [0.999325, 0.447692], "shape": [2]}, "input": {"data": [0, 0.2, 0.5, -0.1, 1, 2], "shape": [6]}, "weights": [{"data": [0.1, 0.4, 0.5, 0.1, 1.0, -2.0, 0.0, 0.3, 0.2, 0.1, 3.0, 0.0], "shape": [6, 2]}, {"data": [0.5, 0.7], "shape": [2]}]}, "core.Dense.5": {"expected": {"data": [6.801113, 0.338274], "shape": [2]}, "input": {"data": [0, 0.2, 0.5, -0.1, 1, 2], "shape": [6]}, "weights": [{"data": [0.1, 0.4, 0.5, 0.1, 1.0, -2.0, 0.0, 0.3, 0.2, 0.1, 3.0, 0.0], "shape": [6, 2]}]}}'

















In [ ]:

Content source: qinwf-nuan/keras-js

Similar notebooks:

notebook.community | gallery | about