def neural_network_test():
'''
Classifier test
'''
x = Placeholder()
w = Variable([1, 1])
b = Variable(-5)
z = add(matmul(w, x), b)
a = Sigmoid(z)
sess = Session()
assert sess.run(operation=a, feed_dict={x: [8, 10]}) > 0.9
assert sess.run(operation=a, feed_dict={x: [4, -10]}) < 0.1
def basic_test():
'''
basic test for z = Ax + b
'''
g = Graph()
A = Variable(10, default_graph=g)
b = Variable(1, default_graph=g)
x = Placeholder(default_graph=g)
y = multiply(A, x)
z = add(y, b)
sess = Session()
result = sess.run(operation=z, feed_dict={x: 10})
print(result)
assert result == 101
def index():
width = request.query.getone('width')
height = request.query.getone('height') or width
color = request.query.getone('color') or 'grey'
response.content_type= 'image/png'
try:
width = int(width)
height = int(height)
except:
width = 320
height = 240
color = 'grey'
print color
return Placeholder(width=width,height=height,color=color).get_binary()
def matrix_multiplication_test():
'''
test for matrix multiplication
'''
A = Variable([[10, 20], [30, 40]])
b = Variable([1, 2])
x = Placeholder()
y = matmul(A, x)
z = add(y, b)
sess = Session()
result = sess.run(operation=z, feed_dict={x: 10})
assert len(result) == 2
assert len(result[0]) == 2
assert result[0][0] == 101
assert result[0][1] == 202
assert result[1][0] == 301
assert result[1][1] == 402
def create_new_placeholder(self, nodes_enough_resource):
placeholder = Placeholder()
# placeholder.node = random.choice(nodes_enough_resource).metadata.name
placeholder.node = nodes_enough_resource[-1].metadata.name
self.placeholders.append(placeholder)
return placeholder
from compgraph import Compgraph
from placeholder import Placeholder
from variable import Variable
import operations as op
from tensor import Tensor
if __name__ == '__main__':
#nuestros tensores para las variables de entrada y el placeholder
X = Tensor([x for x in range(0, 10)]).reshape((10))
dos = Tensor(2)
c = Compgraph()
v_1 = c.add_variable(Variable(dos, "DOS"))
x_1 = c.add_placeholder(Placeholder("X"))
o_1 = c.add_operation(op.sin(x_1))
e_1 = c.add_operation(op.Multiply(o_1, v_1))
print(c.to_dot())
x_1.set_value(X)
res = c.run(e_1)
print(res)
exit(0)
data = make_blobs(n_samples=50, n_features=2, centers=2, random_state=75)
features = data[0]
labels = data[1]
plt.scatter(features[:, 0], features[:, 1], c=labels, cmap='coolwarm')
x = np.linspace(0, 11, 10)
y = -x + 5
plt.plot(x, y)
g = Graph()
graphObject = g.set_as_default()
# Initialize function wx - b | [1,1] * x - 5
x = Placeholder()
graphObject.placeholders.append(x) # append placeholder x
w = Variables([1, 1])
graphObject.variables.append(w) # append variable w
b = Variables(-5)
graphObject.variables.append(b) # append variable b
z = Addition(MatrixMultiplication(w, x, graphObject), b, graphObject)
# Apply activation function
a = Sigmoid(z, graphObject)
# Execute neural network
sess = Session()
print(sess.run(a, {x: [0, -10]}))
plt.show()
def initialize(x, y):
global grid
for i in range(x):
for j in range(y):
grid = [[Placeholder() for _ in range(y)] for _ in range(x)]
