def test_generation(self):
x = Variable(np.array(2.0))
a = F.square(x)
y = add(F.square(a), F.square(a))
y.backward()
self.assertEqual(y.data, np.array(32.0))
self.assertEqual(x.grad.data, np.array(64.0))
def test_backprop_with_numercal_diff(self):
x = Variable(np.random.rand(1))
y = square(x)
y.backward()
num_grad = numercal_diff(square, x)
flg = np.allclose(x.grad.data, num_grad.data)
self.assertTrue(flg)
def test_forward(self):
x = Variable(np.array(2.0))
y = Variable(np.array(3.0))
z = add(F.square(x), F.square(y))
z.backward()
self.assertEqual(z.data, np.array(13.0))
self.assertTrue(isinstance(x.grad, Variable))
a = Variable(np.array(2.0))
b = add(a, a)
b.backward()
a.cleargrad()
b = add(add(a, a), a)
b.backward()
def test__dot_var(self):
a = Variable(np.array(1.0))
b = Variable(np.array(1.0))
c = a + b
d = square(c)
actual = get_dot_graph(d)
self.assertIn(f"{id(d.creator)} -> {id(d)}", actual)
self.assertIn(f"{id(c)} -> {id(d.creator)}", actual)
def test_backward(self):
x = Variable(np.array(3.0))
y = square(x)
y.backward()
expected = np.array(6.0)
if isinstance(x.grad, Variable):
self.assertEqual(x.grad.data, expected)
else:
self.assertEqual(x.grad, expected)
def test_gradient_check(self):
x = Variable(np.random.rand(1))
y = square(x)
y.backward()
num_grad = numerical_diff(square, x)
if isinstance(x.grad, Variable):
flg = np.allclose(x.grad.data, num_grad)
else:
flg = np.allclose(x.grad, num_grad)
self.assertTrue(flg)
if '__file__' in globals():
import os, sys
sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
import numpy as np
from dezero import Variable
from dezero.functions import square, exp
x = Variable(np.array(0.5))
y = square(exp(square(x)))
y.backward()
print(x.grad)
def test_two_branch_diff(self):
x = Variable(np.array(2.0))
a = square(x)
y = add(square(a), square(a))
y.backward()
self.assertEqual(x.grad.data, np.array(64.0))
def test_backward(self):
x = Variable(np.array(3.0))
y = square(x)
y.backward()
expected = np.array(6.0)
self.assertEqual(x.grad.data, expected)
def test_foreard(self):
x = Variable(np.array(2.0))
y = square(x)
expected = np.array(4.0)
self.assertEqual(y.data, expected)
def test_using_config(self):
with no_grad():
x = Variable(np.array(2.0))
y = F.square(x)
self.assertEqual(x.grad, None)
def func(x):
return square(square(x)) + square(square(x))
