76 lines
2.7 KiB
Python
76 lines
2.7 KiB
Python
import numpy as np
|
|
|
|
from keras_core import backend
|
|
from keras_core import ops
|
|
from keras_core import testing
|
|
from keras_core.optimizers.adadelta import Adadelta
|
|
|
|
|
|
class AdadeltaTest(testing.TestCase):
|
|
def test_config(self):
|
|
optimizer = Adadelta(
|
|
learning_rate=0.5,
|
|
rho=0.9,
|
|
epsilon=1e-5,
|
|
)
|
|
self.run_class_serialization_test(optimizer)
|
|
|
|
def test_single_step(self):
|
|
optimizer = Adadelta(learning_rate=0.5)
|
|
grads = ops.array([1.0, 6.0, 7.0, 2.0])
|
|
vars = backend.Variable([1.0, 2.0, 3.0, 4.0])
|
|
optimizer.apply_gradients(zip([grads], [vars]))
|
|
self.assertAllClose(
|
|
vars, [0.9993, 1.9993, 2.9993, 3.9993], rtol=1e-4, atol=1e-4
|
|
)
|
|
|
|
def test_weight_decay(self):
|
|
grads, var1, var2, var3 = (
|
|
ops.zeros(()),
|
|
backend.Variable(2.0),
|
|
backend.Variable(2.0, name="exclude"),
|
|
backend.Variable(2.0),
|
|
)
|
|
optimizer_1 = Adadelta(learning_rate=1.0, weight_decay=0.004)
|
|
optimizer_1.apply_gradients(zip([grads], [var1]))
|
|
|
|
optimizer_2 = Adadelta(learning_rate=1.0, weight_decay=0.004)
|
|
optimizer_2.exclude_from_weight_decay(var_names=["exclude"])
|
|
optimizer_2.apply_gradients(zip([grads, grads], [var1, var2]))
|
|
|
|
optimizer_3 = Adadelta(learning_rate=1.0, weight_decay=0.004)
|
|
optimizer_3.exclude_from_weight_decay(var_list=[var3])
|
|
optimizer_3.apply_gradients(zip([grads, grads], [var1, var3]))
|
|
|
|
self.assertAlmostEqual(var1.numpy(), 1.9760959, decimal=6)
|
|
self.assertAlmostEqual(var2.numpy(), 2.0, decimal=6)
|
|
self.assertAlmostEqual(var3.numpy(), 2.0, decimal=6)
|
|
|
|
def test_correctness_with_golden(self):
|
|
optimizer = Adadelta(learning_rate=1.0, rho=0.8, epsilon=1e-6)
|
|
|
|
x = backend.Variable(np.ones([10]))
|
|
grads = ops.arange(0.1, 1.1, 0.1)
|
|
first_grads = ops.full((10,), 0.01)
|
|
|
|
golden = np.tile(
|
|
[[0.9978], [0.9947], [0.9915], [0.9882], [0.9849]], (1, 10)
|
|
)
|
|
|
|
optimizer.apply_gradients(zip([first_grads], [x]))
|
|
for i in range(5):
|
|
self.assertAllClose(x, golden[i], rtol=5e-4, atol=5e-4)
|
|
optimizer.apply_gradients(zip([grads], [x]))
|
|
|
|
def test_clip_norm(self):
|
|
optimizer = Adadelta(clipnorm=1)
|
|
grad = [np.array([100.0, 100.0])]
|
|
clipped_grad = optimizer._clip_gradients(grad)
|
|
self.assertAllClose(clipped_grad[0], [2**0.5 / 2, 2**0.5 / 2])
|
|
|
|
def test_clip_value(self):
|
|
optimizer = Adadelta(clipvalue=1)
|
|
grad = [np.array([100.0, 100.0])]
|
|
clipped_grad = optimizer._clip_gradients(grad)
|
|
self.assertAllClose(clipped_grad[0], [1.0, 1.0])
|