In [1]:
import numpy as np
from keras.models import Model
from keras.layers import Input, Dense, RepeatVector
from keras.layers.merge import Add, Subtract, Multiply, Average, Maximum, Minimum, Concatenate, Dot
from keras import backend as K
import json
from collections import OrderedDict
In [2]:
def format_decimal(arr, places=6):
return [round(x * 10**places) / 10**places for x in arr]
In [3]:
DATA = OrderedDict()
[merge.Minimum.0]
In [4]:
random_seed = 100
data_in_shape = (6,)
layer_0 = Input(shape=data_in_shape)
layer_1a = Dense(2, activation='linear')(layer_0)
layer_1b = Dense(2, activation='linear')(layer_0)
layer_2 = Minimum()([layer_1a, layer_1b])
model = Model(inputs=layer_0, outputs=layer_2)
np.random.seed(random_seed)
data_in = np.expand_dims(2 * np.random.random(data_in_shape) - 1, axis=0)
# set weights to random (use seed for reproducibility)
weights = []
for i, w in enumerate(model.get_weights()):
np.random.seed(random_seed + i)
weights.append(2 * np.random.random(w.shape) - 1)
model.set_weights(weights)
result = model.predict(data_in)
data_out_shape = result[0].shape
data_in_formatted = format_decimal(data_in.ravel().tolist())
data_out_formatted = format_decimal(result[0].ravel().tolist())
DATA['merge.Minimum.0'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in weights],
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[merge.Minimum.1]
In [5]:
random_seed = 100
data_in_shape = (6,)
layer_0 = Input(shape=data_in_shape)
layer_1a = Dense(2, activation='linear')(layer_0)
layer_1b = Dense(2, activation='linear')(layer_0)
layer_1c = Dense(2, activation='linear')(layer_0)
layer_2 = Minimum()([layer_1a, layer_1b, layer_1c])
model = Model(inputs=layer_0, outputs=layer_2)
np.random.seed(random_seed)
data_in = np.expand_dims(2 * np.random.random(data_in_shape) - 1, axis=0)
# set weights to random (use seed for reproducibility)
weights = []
for i, w in enumerate(model.get_weights()):
np.random.seed(random_seed + i)
weights.append(2 * np.random.random(w.shape) - 1)
model.set_weights(weights)
result = model.predict(data_in)
data_out_shape = result[0].shape
data_in_formatted = format_decimal(data_in.ravel().tolist())
data_out_formatted = format_decimal(result[0].ravel().tolist())
DATA['merge.Minimum.1'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in weights],
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[merge.Minimum.2]
In [6]:
random_seed = 100
data_in_shape = (6,)
layer_0 = Input(shape=data_in_shape)
layer_1a = Dense(2, activation='linear')(layer_0)
layer_1b = Dense(2, activation='linear')(layer_0)
layer_1c = Dense(2, activation='linear')(layer_0)
layer_1d = Dense(2, activation='linear')(layer_0)
layer_2 = Minimum()([layer_1a, layer_1b, layer_1c, layer_1d])
model = Model(inputs=layer_0, outputs=layer_2)
np.random.seed(random_seed)
data_in = np.expand_dims(2 * np.random.random(data_in_shape) - 1, axis=0)
# set weights to random (use seed for reproducibility)
weights = []
for i, w in enumerate(model.get_weights()):
np.random.seed(random_seed + i)
weights.append(2 * np.random.random(w.shape) - 1)
model.set_weights(weights)
result = model.predict(data_in)
data_out_shape = result[0].shape
data_in_formatted = format_decimal(data_in.ravel().tolist())
data_out_formatted = format_decimal(result[0].ravel().tolist())
DATA['merge.Minimum.2'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'weights': [{'data': format_decimal(w.ravel().tolist()), 'shape': w.shape} for w in weights],
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
In [7]:
import os
filename = '../../../test/data/layers/merge/Minimum.json'
if not os.path.exists(os.path.dirname(filename)):
os.makedirs(os.path.dirname(filename))
with open(filename, 'w') as f:
json.dump(DATA, f)
In [8]:
print(json.dumps(DATA))