In [1]:
import numpy as np
from keras.models import Model
from keras.layers import Input
from keras.layers.pooling import AveragePooling2D
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()
[pooling.AveragePooling2D.0] input 6x6x3, pool_size=(2, 2), strides=None, padding='valid', data_format='channels_last'
In [4]:
data_in_shape = (6, 6, 3)
L = AveragePooling2D(pool_size=(2, 2), strides=None, padding='valid', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(270)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.0'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.1] input 6x6x3, pool_size=(2, 2), strides=(1, 1), padding='valid', data_format='channels_last'
In [5]:
data_in_shape = (6, 6, 3)
L = AveragePooling2D(pool_size=(2, 2), strides=(1, 1), padding='valid', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(271)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.1'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.2] input 6x7x3, pool_size=(2, 2), strides=(2, 1), padding='valid', data_format='channels_last'
In [6]:
data_in_shape = (6, 7, 3)
L = AveragePooling2D(pool_size=(2, 2), strides=(2, 1), padding='valid', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(272)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.2'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.3] input 6x6x3, pool_size=(3, 3), strides=None, padding='valid', data_format='channels_last'
In [7]:
data_in_shape = (6, 6, 3)
L = AveragePooling2D(pool_size=(3, 3), strides=None, padding='valid', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(273)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.3'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.4] input 6x6x3, pool_size=(3, 3), strides=(3, 3), padding='valid', data_format='channels_last'
In [8]:
data_in_shape = (6, 6, 3)
L = AveragePooling2D(pool_size=(3, 3), strides=(3, 3), padding='valid', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(274)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.4'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.5] input 6x6x3, pool_size=(2, 2), strides=None, padding='same', data_format='channels_last'
In [9]:
data_in_shape = (6, 6, 3)
L = AveragePooling2D(pool_size=(2, 2), strides=None, padding='same', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(275)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.5'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.6] input 6x6x3, pool_size=(2, 2), strides=(1, 1), padding='same', data_format='channels_last'
In [10]:
data_in_shape = (6, 6, 3)
L = AveragePooling2D(pool_size=(2, 2), strides=(1, 1), padding='same', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(276)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.6'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.7] input 6x7x3, pool_size=(2, 2), strides=(2, 1), padding='same', data_format='channels_last'
In [11]:
data_in_shape = (6, 7, 3)
L = AveragePooling2D(pool_size=(2, 2), strides=(2, 1), padding='same', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(277)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.7'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.8] input 6x6x3, pool_size=(3, 3), strides=None, padding='same', data_format='channels_last'
In [12]:
data_in_shape = (6, 6, 3)
L = AveragePooling2D(pool_size=(3, 3), strides=None, padding='same', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(278)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.8'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.9] input 6x6x3, pool_size=(3, 3), strides=(3, 3), padding='same', data_format='channels_last'
In [13]:
data_in_shape = (6, 6, 3)
L = AveragePooling2D(pool_size=(3, 3), strides=(3, 3), padding='same', data_format='channels_last')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(279)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.9'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.10] input 5x6x3, pool_size=(3, 3), strides=(2, 2), padding='valid', data_format='channels_first'
In [14]:
data_in_shape = (5, 6, 3)
L = AveragePooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid', data_format='channels_first')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(280)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.10'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.11] input 5x6x3, pool_size=(3, 3), strides=(1, 1), padding='same', data_format='channels_first'
In [15]:
data_in_shape = (5, 6, 3)
L = AveragePooling2D(pool_size=(3, 3), strides=(1, 1), padding='same', data_format='channels_first')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(281)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.11'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[pooling.AveragePooling2D.12] input 4x6x4, pool_size=(2, 2), strides=None, padding='valid', data_format='channels_first'
In [16]:
data_in_shape = (4, 6, 4)
L = AveragePooling2D(pool_size=(2, 2), strides=None, padding='valid', data_format='channels_first')
layer_0 = Input(shape=data_in_shape)
layer_1 = L(layer_0)
model = Model(inputs=layer_0, outputs=layer_1)
# set weights to random (use seed for reproducibility)
np.random.seed(282)
data_in = 2 * np.random.random(data_in_shape) - 1
result = model.predict(np.array([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())
print('')
print('in shape:', data_in_shape)
print('in:', data_in_formatted)
print('out shape:', data_out_shape)
print('out:', data_out_formatted)
DATA['pooling.AveragePooling2D.12'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
In [17]:
print(json.dumps(DATA))
In [ ]: