def test_quadratic():
x = nf.initialized_var('x', np.array([[0.07], [0.4], [0.1]]))
A = nf.constant(np.array([[2, -1, -2], [-1, 1, 0], [-2, 0, 4]]))
B = nf.constant(np.array([[1, 0, 0], [0, 0, 0], [0, 0, 0]]))
b = nf.placeholder(shape=(3, 1))
quadratic = x.T() @ A @ x
linear = B @ x - b
squared_linear = nf.mat_sum(linear)**2
expr = quadratic + squared_linear
cost_function = nf.as_scalar(expr) + 7
cost = Graph(cost_function)
cost.placeholders = {
b: np.array([1, 0, 0]).reshape(3, 1).astype('float32')
}
cost.initialize_variables()
optimizer = gd.GradientDescentOptimizer(0.1)
optimizer.prepare_and_check(cost)
for i in range(500):
optimizer.run()
np.testing.assert_allclose(cost.evaluate(), 7.)
np.testing.assert_allclose(x.value, np.array([[1.], [1.], [.5]]))
def train(self,
x_train,
y_train,
num_iterations=2000,
learning_rate=0.5,
print_cost=True):
self.cost_graph.placeholders = {self.X: x_train, self.Y: y_train}
self.cost_graph.initialize_variables()
optimizer = gd.GradientDescentOptimizer(learning_rate)
optimizer.prepare_and_check(self.cost_graph)
costs = []
for i in range(num_iterations):
optimizer.run()
if i % ITERATIONS_UNIT == 0:
costs.append(optimizer.cost)
if print_cost and i % ITERATIONS_UNIT == 0:
print(f"Cost after iteration {i}: {optimizer.cost}")
return costs
weights = f.var("W" + str(layer_num + 1), self.weight_initializer,
shape=(cnt_neurons, cnt_features))
biases = f.var("b" + str(layer_num + 1), init.ZeroInitializer(),
shape=(cnt_neurons, 1))
return f.fully_connected(features, weights, biases,
first_layer=(layer_num == 0))
def train(self, x_train, y_train, *,
num_iterations=15_000,
learning_rate=0.01,
print_cost=True):
env.seed(3)
self.cost_graph.placeholders = {self.X: x_train, self.Y: y_train}
self.cost_graph.initialize_variables()
optimizer = gd.GradientDescentOptimizer(learning_rate)
optimizer.prepare_and_check(self.cost_graph)
costs = []
for i in range(num_iterations + 1):
optimizer.run()
if i % 1000 == 0:
costs.append(optimizer.cost)
if print_cost and i % 1000 == 0:
print(f"Cost after iteration {i}: {optimizer.cost}")
return costs
def predict(self, x_test):
self.prediction_graph.placeholders = {self.X: x_test}