def test_forward1(self):
layer = ConvLayer(1, 1, 3)
x = fake_data((1, 1, 3, 3))
layer.W = fake_data((1, 1, 3, 3))
layer.b = fake_data(layer.b.shape)
y = layer.forward(x)
should_be = np.array([[[[58., 100., 70.], [132., 204., 132.],
[70., 100., 58.]]]])
self.assertTrue(np.allclose(y, should_be))
def test_forward4(self):
h = 5
layer = ConvLayer(2, 5, h)
x = fake_data((2, 2, 8, 8))
layer.W = fake_data((5, 2, h, h))
layer.b = fake_data(layer.b.shape)
#print "b = ", layer.b
y = layer.forward(x)
from test4_result import t4_should_be
#print "y = ", y
#print "should_be = ", t4_should_be
self.assertTrue(np.allclose(y, t4_should_be))
def test_forward2(self):
layer = ConvLayer(2, 1, 3)
x = fake_data((1, 2, 4, 4))
layer.W = fake_data((1, 2, 3, 3))
layer.b = fake_data(layer.b.shape)
y = layer.forward(x)
should_be = np.array([[[[1196., 1796., 1916., 1264.],
[1881., 2793., 2946., 1923.],
[2313., 3405., 3558., 2307.],
[1424., 2072., 2156., 1380.]]]])
self.assertTrue(np.allclose(y, should_be))
def test_forward1(self):
layer = FlattenLayer()
x = fake_data((1, 2, 3, 3))
y = layer.forward(x)
self.assertTrue(y.shape == (1, 18))
def test_backward3(self):
self.x = fake_data((2, 3, 5, 5))
nm_x_grad = numerical_gradient(self.layer, self.x, self.x)
self.layer.forward(self.x)
y = np.ones((2, 3, 2, 2))
x_grad = self.layer.backward(y)
self.assertTrue(np.allclose(nm_x_grad, x_grad))
def test_backward4(self):
h = 5
layer = ConvLayer(2, 5, h)
x = fake_data((2, 2, 8, 8))
layer.W = fake_data((5, 2, h, h))
layer.b = fake_data(layer.b.shape)
y = layer.forward(x)
x_grad = layer.backward(np.ones_like(y))
nm_x_grad = numerical_gradient(layer, x, x)
nm_w_grad = numerical_gradient(layer, x, layer.W)
nm_b_grad = numerical_gradient(layer, x, layer.b)
self.assertTrue(np.allclose(nm_x_grad, x_grad))
self.assertTrue(np.allclose(nm_w_grad, layer.W_grad))
self.assertTrue(np.allclose(nm_b_grad, layer.b_grad))
def test_backward3_5(self):
layer = ConvLayer(5, 3, 3)
x = fake_data((2, 5, 3, 3))
layer.W = fake_data(layer.W.shape)
layer.b = fake_data(layer.b.shape)
y = layer.forward(x)
x_grad = layer.backward(np.ones_like(y))
# do numerical gradients
nm_x_grad = numerical_gradient(layer, x, x)
nm_w_grad = numerical_gradient(layer, x, layer.W)
nm_b_grad = numerical_gradient(layer, x, layer.b)
self.assertTrue(np.allclose(nm_x_grad, x_grad))
self.assertTrue(np.allclose(nm_w_grad, layer.W_grad))
self.assertTrue(np.allclose(nm_b_grad, layer.b_grad))
def test_forward3(self):
layer = ConvLayer(2, 2, 3)
x = fake_data((1, 2, 4, 4))
layer.W = fake_data((2, 2, 3, 3))
layer.b = fake_data(layer.b.shape)
y = layer.forward(x)
should_be = np.array([[[[1196., 1796., 1916., 1264.],
[1881., 2793., 2946., 1923.],
[2313., 3405., 3558., 2307.],
[1424., 2072., 2156., 1380.]],
[[2709., 4173., 4509., 3065.],
[4582., 7006., 7483., 5056.],
[5878., 8914., 9391., 6304.],
[4089., 6177., 6477., 4333.]]]])
self.assertTrue(np.allclose(y, should_be))
def test_backward5(self):
h = 5
layer = ConvLayer(2, 5, h)
x = fake_data((2, 2, 8, 8))
layer.W = fake_data((5, 2, h, h))
layer.b = fake_data(layer.b.shape)
y = layer.forward(x)
y_grad = fake_data(y.shape)
x_grad = layer.backward(y_grad)
nm_x_grad = numerical_gradient(layer, x, x, y_grad)
nm_w_grad = numerical_gradient(layer, x, layer.W, y_grad)
nm_b_grad = numerical_gradient(layer, x, layer.b, y_grad)
self.assertTrue(np.allclose(nm_x_grad, x_grad))
self.assertTrue(np.allclose(nm_w_grad, layer.W_grad))
self.assertTrue(np.allclose(nm_b_grad, layer.b_grad))
def test_backward1(self):
layer = FlattenLayer()
x = fake_data((1, 2, 3, 3))
y = layer.forward(x)
x_grad = layer.backward(np.ones_like(y))
# do numerical gradients
nm_x_grad = numerical_gradient(layer, x, x)
self.assertTrue(np.allclose(nm_x_grad, x_grad))
def test_backward2(self):
layer = ConvLayer(2, 1, 3)
x = fake_data((1, 2, 4, 4))
layer.W = fake_data((1, 2, 3, 3))
layer.b = fake_data(layer.b.shape)
y = layer.forward(x)
x_grad = layer.backward(np.ones_like(y))
# do numerical gradients
nm_x_grad = numerical_gradient(layer, x, x)
nm_w_grad = numerical_gradient(layer, x, layer.W)
nm_b_grad = numerical_gradient(layer, x, layer.b)
self.assertTrue(np.allclose(nm_x_grad, x_grad))
print "Pass x_grad"
self.assertTrue(np.allclose(nm_w_grad, layer.W_grad))
print "Pass w_grad"
self.assertTrue(np.allclose(nm_b_grad, layer.b_grad))
print "Pass b_grad"
def test_backward(self):
out = self.layer.forward(self.x)
y = fake_data((1, 3, 2, 2))
x_grad = self.layer.backward(y)
should_be = np.array([[[[0., 0., 0., 0.], [0., 0., 0., 1.],
[0., 0., 0., 0.], [0., 2., 0., 3.]],
[[0., 0., 0., 0.], [0., 4., 0., 5.],
[0., 0., 0., 0.], [0., 6., 0., 7.]],
[[0., 0., 0., 0.], [0., 8., 0., 9.],
[0., 0., 0., 0.], [0., 10., 0., 11.]]]])
self.assertTrue(np.allclose(should_be, x_grad))
def test_backward1(self):
layer = ConvLayer(1, 1, 3)
x = fake_data((1, 1, 8, 8))
layer.W = fake_data((1, 1, 3, 3))
layer.b = fake_data(layer.b.shape)
y = layer.forward(x)
x_grad = layer.backward(np.ones_like(y))
# do numerical gradients
nm_x_grad = numerical_gradient(layer, x, x)
nm_w_grad = numerical_gradient(layer, x, layer.W)
nm_b_grad = numerical_gradient(layer, x, layer.b)
# note that this does not check the gradients of the padded elements
self.assertTrue(np.allclose(nm_x_grad, x_grad))
self.assertTrue(np.allclose(nm_w_grad, layer.W_grad))
self.assertTrue(np.allclose(nm_b_grad, layer.b_grad))
def setUp(self):
self.layer = MaxPoolLayer()
self.x = fake_data((1, 3, 4, 4))
def test_bigger(self):
self.x = fake_data((2, 4, 8, 8))
out = self.layer.forward(self.x)
from max_pool_big import mp_result
self.assertTrue(np.allclose(mp_result, out))