def test_jacobian_cnn_11_11(self):
image = [random.randint(0, 255) for _ in range(2)]
image = Image(image_data=image, shape=(1, 2))
cnn_a = CNN(reLU(), (1, 1), (0, 0), name='a')
cnn_b = CNN(reLU(), (1, 1), (0, 0), name='b')
model = Model(layers=[
image,
cnn_a,
cnn_b,
])
self._run_derivatives_test(model)
def test_jacobian_cnn_33_33_33_dense_11(self):
image = [random.randint(0, 255) for _ in range(49)]
image = Image(image_data=image)
cnn_a = CNN(reLU(), (3, 3), name='a')
cnn_b = CNN(reLU(), (3, 3), name='b')
cnn_c = CNN(reLU(), (3, 3), name='c')
dense = Dense(reLU(), (1, 1), name='d')
model = Model(layers=[
image,
cnn_a,
cnn_b,
cnn_c,
dense,
])
self._run_derivatives_test(model)
def test_jacobian_dense_11_cnn_11(self):
image = [random.randint(0, 255) for _ in range(1)]
small_image = Image(image_data=image)
dense = Dense(reLU(), (1, 1))
cnn = CNN(reLU(), (1, 1), (0, 0))
model = Model(layers=[small_image, cnn, dense])
self._run_derivatives_test(model)
def test_mnist_image(self):
image_data = [
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 44.25, 122.75, 126.5, 70.5,
0.0, 0.0, 0.0, 0.0, 0.0, 6.5, 1.5, 0.0, 16.75, 203.75, 249.5,
252.0, 252.0, 246.5, 214.75, 37.5, 0.0, 0.0, 0.0, 25.25, 6.0, 0.0,
7.0, 123.5, 166.75, 162.25, 201.25, 252.5, 181.5, 9.25, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0, 30.0, 167.5, 248.75, 240.5, 129.0, 27.5,
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 212.75, 252.5, 208.75,
26.5, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 34.25,
71.5, 214.75, 202.0, 31.5, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 13.25, 169.5, 167.25, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 148.25, 190.5, 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 12.75, 210.0, 159.5, 65.75, 167.5, 209.75, 252.5, 78.25,
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 3.25, 168.0, 252.5, 251.25, 238.25,
163.75, 58.75, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 15.75,
106.5, 60.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
]
model = Model(layers=[
Image(image_data=image_data, maximum=256),
CNN(reLU(), (3, 3)),
Dense(reLU(), (3, 1)),
Category([1, 2, 3]),
])
model.compile(build=True)
model.jacobian()
weights = model.weights()
derivatives = [w.derivative() for w in weights]
pass
def test_jacobian_cnn_31(self):
image = [random.randint(0, 255) for _ in range(3)]
model = Model(layers=[
Image(image_data=image, shape=(3, 1)),
CNN(reLU(), (3, 1), (0, 0), name='a'),
])
weights = self._run_derivatives_test(model)
self.assertEqual(len(weights), 7)
def test_jacobian_cnn_31_dense_11(self):
random.seed(44009)
image = [random.randint(0, 255) for _ in range(3)]
model = Model(layers=[
Image(image_data=image, shape=(3, 1)),
CNN(reLU(), (3, 1), name='a'),
Dense(reLU(), (1, 1), name='d'),
])
self._run_derivatives_test(model)
from j2learn.data.mnist_images import MNISTData from j2learn.function.function import reLU from j2learn.layer.category import Category from j2learn.layer.cnn import CNN from j2learn.layer.dense import Dense from j2learn.layer.image import Image from j2learn.model.model import Model from j2learn.etc.tools import finite_difference mndata = MNISTData(path='../mnist') images, labels = mndata.training() r = 49 # a nice number three image_layer = Image(image_data=images[r], label=labels[r]) cnn = CNN(reLU(), (3, 3), (0, 0)) dense = Dense(reLU(), (10, 1)) category = Category([i for i in range(10)]) model = Model(layers=[image_layer, cnn, dense, category]) model.compile(build=True) cat = model.predict() print(cat) prob = model.probability() print(prob) n_weights = model.weight_count() gradient = 0 i = 0
from j2learn.data.mnist_images import MNISTData
from j2learn.function.function import reLU
from j2learn.layer.category import Category
from j2learn.layer.cnn import CNN
from j2learn.layer.dense import Dense
from j2learn.layer.image import Image
mndata = MNISTData(path='../mnist')
images, labels = mndata.training()
r = 49 # a nice number three
image_layer = Image(image_data=images[r], label=labels[r])
print(image_layer.display())
### test a non-convoluted CNN. Need the same output
identity_cnn = CNN(reLU(), (1, 1), (0, 0), image_layer, weight=1)
for i in range(identity_cnn.shape()[0] * identity_cnn.shape()[1]):
assert identity_cnn.node(i).value() == identity_cnn._underlying_layer.node(
i).value()
print(identity_cnn.display())
### test convolution
first_cnn = CNN(reLU(), (3, 3), (0, 0), identity_cnn)
print(first_cnn.display(threshold=0.5))
second_cnn = CNN(reLU(), (3, 3), (0, 0), first_cnn)
print(second_cnn.display(threshold=0.5))
### more layers
dense = Dense(reLU(), (10, 1), second_cnn)
category = Category([i for i in range(10)], dense)
print(category.node(0).value())
def test_jacobian_dense_21_cnn_12(self):
image = Image(image_data=[random.randint(0, 255) for _ in range(4)])
dense = Dense(reLU(), (2, 1))
cnn = CNN(reLU(), (1, 2), (0, 0))
model = Model(layers=[image, cnn, dense])
self._run_derivatives_test(model)
def test_jacobian_cnn_11(self):
image = [random.randint(0, 255) for _ in range(2)]
image = Image(image_data=image, shape=(2, 1))
cnn = CNN(reLU(), (1, 1), (0, 0))
model = Model(layers=[image, cnn])
self._run_derivatives_test(model)
import random
from j2learn.etc.tools import finite_differences
from j2learn.function.function import reLU
from j2learn.layer.cnn import CNN
from j2learn.layer.dense import Dense
from j2learn.layer.category import Category
from j2learn.layer.image import Image
from j2learn.model.model import Model
pixels = 81
image = Image(image_data=[random.randint(59, 59) for _ in range(pixels)])
cnn_a = CNN(reLU(), (3, 3), name='a')
cnn_b = CNN(reLU(), (3, 3), name='b')
cnn_c = CNN(reLU(), (3, 3), name='c')
dense = Dense(reLU(), (10, 1), name='d')
category = Category([i for i in range(10)])
model = Model(layers=[
image,
cnn_a,
cnn_b,
cnn_c,
dense,
category,
])
model.compile(build=True)
v = model.value()
# v = model.probability()
analytic_jacobian = model.jacobian()