def test_backward(self):
x = Variable(np.array(2.0))
a = square(x)
y = add(square(a), square(a))
y.backward()
self.assertEqual(y.data, 32.0)
self.assertEqual(x.grad, 64.0)
def test_config(self):
# 学習時
self.assertTrue(Config.enable_backprop)
x = Variable(np.ones((100, 100, 100)))
y = square(square(square(x)))
y.backward()
with no_grad():
x = Variable(np.array(2.0))
y = square(x)
self.assertFalse(Config.enable_backprop)
self.assertTrue(Config.enable_backprop)
def test_gradient_check(self):
x = Variable(np.random.rand(1))
y = square(x)
y.backward()
num_grad = numerical_diff(square, x)
flag = np.allclose(x.grad, num_grad)
self.assertTrue(flag)
def test_forward(self):
x = Variable(np.array(2.0))
y = square(x)
expected = np.array(4.0)
self.assertEqual(y.data, expected)
def test_backward(self):
x = Variable(np.array(3.0))
y = square(x)
y.backward()
expected = np.array(6.0)
self.assertEqual(x.grad, expected)
def test_wrapper():
x = Variable(np.array([1, 2]))
y = exp(square(x))
y.backward()
return x.grad