In [1]:
import numpy as np
from keras.models import Model
from keras.layers import Input
from keras.layers.convolutional import Cropping2D
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()
[convolutional.Cropping2D.0] cropping ((1,1),(1,1)) on 3x5x4 input, data_format='channels_last'
In [4]:
data_in_shape = (3, 5, 4)
L = Cropping2D(cropping=((1,1),(1, 1)), 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(250)
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['convolutional.Cropping2D.0'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[convolutional.Cropping2D.1] cropping ((1,1),(1,1)) on 3x5x4 input, data_format='channels_first'
In [5]:
data_in_shape = (3, 5, 4)
L = Cropping2D(cropping=((1,1),(1,1)), 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(251)
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['convolutional.Cropping2D.1'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[convolutional.Cropping2D.2] cropping ((4,2),(3,1)) on 8x7x6 input, data_format='channels_last'
In [6]:
data_in_shape = (8, 7, 6)
L = Cropping2D(cropping=((4,2),(3,1)), 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(252)
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['convolutional.Cropping2D.2'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[convolutional.Cropping2D.3] cropping ((4,2),(3,1)) on 8x7x6 input, data_format='channels_first'
In [7]:
data_in_shape = (8, 7, 6)
L = Cropping2D(cropping=((4,2),(3,1)), 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(253)
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['convolutional.Cropping2D.3'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[convolutional.Cropping2D.4] cropping (2,3) on 8x7x6 input, data_format='channels_last'
In [8]:
data_in_shape = (8, 7, 6)
L = Cropping2D(cropping=(2,3), 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(254)
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['convolutional.Cropping2D.4'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
[convolutional.Cropping2D.5] cropping 4 on 8x7x6 input, data_format='channels_last'
In [9]:
data_in_shape = (8, 7, 6)
L = Cropping2D(cropping=1, 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(255)
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['convolutional.Cropping2D.5'] = {
'input': {'data': data_in_formatted, 'shape': data_in_shape},
'expected': {'data': data_out_formatted, 'shape': data_out_shape}
}
In [10]:
print(json.dumps(DATA))
In [ ]: