def test_L2NormPenaltyNode(self):
max_allowed_rel_err = 1e-5
l2_reg = np.array(4.0)
w = nodes.ValueNode("w")
l2_norm_node = nodes.L2NormPenaltyNode(l2_reg, w, "l2 norm node")
d = (5)
init_vals = {"w":np.array(np.random.standard_normal(d))}
max_rel_err = test_utils.test_node_backward(l2_norm_node, init_vals, delta=1e-7)
self.assertTrue(max_rel_err < max_allowed_rel_err)
def test_backward_SquaredL2DistanceNode_2d_array(self):
dims = (10, 10)
init_vals = {
"a": np.array(np.random.standard_normal(dims)),
"b": np.array(np.random.standard_normal(dims)),
}
max_rel_err = test_utils.test_node_backward(self.l2_node,
init_vals,
delta=1e-7)
self.assertTrue(max_rel_err < self.max_allowed_rel_err)
def test_TanhNode(self):
a = nodes.ValueNode(node_name="a")
tanh_node = nodes.TanhNode(a, "tanh")
m = 8
d = 5
init_vals = {"a":np.random.randn(m,d)}
max_rel_err = test_utils.test_node_backward(tanh_node, init_vals, delta=1e-7)
max_allowed_rel_err = 1e-5
self.assertTrue(max_rel_err < max_allowed_rel_err)
def test_backward_VectorScalarAffineNode(self):
n_ftrs = 5
init_vals = {
"w": np.random.randn(n_ftrs),
"x": np.random.randn(n_ftrs),
"b": np.array(np.random.randn()),
}
max_rel_err = test_utils.test_node_backward(self.affine_node,
init_vals,
delta=1e-7)
self.assertTrue(max_rel_err < self.max_allowed_rel_err)
def test_backward_SquaredL2DistanceNode_1d_array(self):
# Not used for linear regression, but can also apply the
# node to higher dimensional arrays
dims = 10
init_vals = {
"a": np.array(np.random.standard_normal(dims)),
"b": np.array(np.random.standard_normal(dims)),
}
max_rel_err = test_utils.test_node_backward(self.l2_node,
init_vals,
delta=1e-7)
self.assertTrue(max_rel_err < self.max_allowed_rel_err)
def test_SumNode(self):
max_allowed_rel_err = 1e-5
a = nodes.ValueNode("a")
b = nodes.ValueNode("b")
dims = ()
a_val = np.array(np.random.standard_normal(dims))
b_val = np.array(np.random.standard_normal(dims))
sum_node = nodes.SumNode(a, b, "sum node")
init_vals = {"a":a_val, "b":b_val}
max_rel_err = test_utils.test_node_backward(sum_node, init_vals, delta=1e-7)
self.assertTrue(max_rel_err < max_allowed_rel_err)
def test_AffineNode(self):
W = nodes.ValueNode(node_name="W")
x = nodes.ValueNode(node_name="x")
b = nodes.ValueNode(node_name="b")
affine_node = nodes.AffineNode(W, x, b, "affine")
m = 8
d = 5
init_vals = {"W":np.random.randn(m,d),
"b":np.random.randn(m),
"x":np.random.randn(d)}
max_rel_err = test_utils.test_node_backward(affine_node, init_vals, delta=1e-7)
max_allowed_rel_err = 1e-5
self.assertTrue(max_rel_err < max_allowed_rel_err)
def test_backward_SquaredL2DistanceNode(self):
max_allowed_rel_err = 1e-5
a = nodes.ValueNode("a")
b = nodes.ValueNode("b")
node = nodes.SquaredL2DistanceNode(a, b, "L2 dist node")
dims = ()
init_vals = {
"a": np.array(np.random.standard_normal(dims)),
"b": np.array(np.random.standard_normal(dims))
}
max_rel_err = test_utils.test_node_backward(node,
init_vals,
delta=1e-7)
self.assertTrue(max_rel_err < max_allowed_rel_err)
# Not used for linear regression, but can also apply the
# node to higher dimensional arrays
dims = (10)
init_vals = {
"a": np.array(np.random.standard_normal(dims)),
"b": np.array(np.random.standard_normal(dims))
}
max_rel_err = test_utils.test_node_backward(node,
init_vals,
delta=1e-7)
self.assertTrue(max_rel_err < max_allowed_rel_err)
dims = (10, 10)
init_vals = {
"a": np.array(np.random.standard_normal(dims)),
"b": np.array(np.random.standard_normal(dims))
}
max_rel_err = test_utils.test_node_backward(node,
init_vals,
delta=1e-7)
self.assertTrue(max_rel_err < max_allowed_rel_err)
def test_backward_VectorScalarAffineNode(self):
max_allowed_rel_err = 1e-5
w = nodes.ValueNode("w")
x = nodes.ValueNode("x")
b = nodes.ValueNode("b")
affine_node = nodes.VectorScalarAffineNode(x, w, b, "affine node")
num_ftrs = 5
init_vals = {
"w": np.random.randn(num_ftrs),
"x": np.random.randn(num_ftrs),
"b": np.array(np.random.randn())
}
max_rel_err = test_utils.test_node_backward(affine_node,
init_vals,
delta=1e-7)
self.assertTrue(max_rel_err < max_allowed_rel_err)
