def test_tfoptimizer():
from keras import constraints
import tensorflow as tf
if tf.__version__.startswith('1.'):
optimizer = optimizers.TFOptimizer(tf.train.AdamOptimizer())
else:
optimizer = tf.keras.optimizers.Adam()
model = Sequential()
model.add(
Dense(num_classes,
input_shape=(3, ),
kernel_constraint=constraints.MaxNorm(1)))
model.compile(loss='mean_squared_error', optimizer=optimizer)
model.fit(np.random.random((5, 3)),
np.random.random((5, num_classes)),
epochs=1,
batch_size=5,
verbose=0)
if tf.__version__.startswith('1.'):
with pytest.raises(NotImplementedError):
optimizer.weights
with pytest.raises(NotImplementedError):
optimizer.get_config()
with pytest.raises(NotImplementedError):
optimizer.from_config(None)
def test_dense():
layer_test(layers.Dense, kwargs={'units': 3}, input_shape=(3, 2))
layer_test(layers.Dense, kwargs={'units': 3}, input_shape=(3, 4, 2))
layer_test(layers.Dense, kwargs={'units': 3}, input_shape=(None, None, 2))
layer_test(layers.Dense, kwargs={'units': 3}, input_shape=(3, 4, 5, 2))
layer_test(layers.Dense,
kwargs={
'units': 3,
'kernel_regularizer': regularizers.l2(0.01),
'bias_regularizer': regularizers.l1(0.01),
'activity_regularizer': regularizers.L1L2(l1=0.01, l2=0.01),
'kernel_constraint': constraints.MaxNorm(1),
'bias_constraint': constraints.max_norm(1)
},
input_shape=(3, 2))
layer = layers.Dense(3,
kernel_regularizer=regularizers.l1(0.01),
bias_regularizer='l1')
layer.build((None, 4))
assert len(layer.losses) == 2
def test_maxout_dense():
from keras import regularizers
from keras import constraints
layer_test(core.MaxoutDense, kwargs={'output_dim': 3}, input_shape=(3, 2))
layer_test(core.MaxoutDense,
kwargs={
'output_dim': 3,
'W_regularizer': regularizers.l2(0.01),
'b_regularizer': regularizers.l1(0.01),
'activity_regularizer': regularizers.activity_l2(0.01),
'W_constraint': constraints.MaxNorm(1),
'b_constraint': constraints.MaxNorm(1)
},
input_shape=(3, 2))
def test_tfoptimizer_pass_correct_named_params_to_native_tensorflow_optimizer(
):
from keras import constraints
from tensorflow import train
class MyTfOptimizer(train.Optimizer):
wrapping_optimizer = train.AdamOptimizer()
def compute_gradients(self, loss, **kwargs):
return super(MyTfOptimizer, self).compute_gradients(loss, **kwargs)
def apply_gradients(self, grads_and_vars, **kwargs):
return self.wrapping_optimizer.apply_gradients(
grads_and_vars, **kwargs)
my_tf_optimizer = MyTfOptimizer(use_locking=False, name='MyTfOptimizer')
optimizer = optimizers.TFOptimizer(my_tf_optimizer)
model = Sequential()
model.add(
Dense(num_classes,
input_shape=(3, ),
kernel_constraint=constraints.MaxNorm(1)))
model.compile(loss='mean_squared_error', optimizer=optimizer)
model.fit(np.random.random((5, 3)),
np.random.random((5, num_classes)),
epochs=1,
batch_size=5,
verbose=0)
def test_timedistributeddense():
from keras import regularizers
from keras import constraints
layer_test(core.TimeDistributedDense,
kwargs={'output_dim': 2, 'input_length': 2},
input_shape=(3, 2, 3))
layer_test(core.TimeDistributedDense,
kwargs={'output_dim': 3,
'W_regularizer': regularizers.l2(0.01),
'b_regularizer': regularizers.l1(0.01),
'activity_regularizer': regularizers.activity_l2(0.01),
'W_constraint': constraints.MaxNorm(1),
'b_constraint': constraints.MaxNorm(1)},
input_shape=(3, 2, 3))
def test_cosinedense():
from keras import regularizers
from keras import constraints
from keras.models import Sequential
layer_test(core.CosineDense, kwargs={'units': 3}, input_shape=(3, 2))
layer_test(core.CosineDense, kwargs={'units': 3}, input_shape=(3, 4, 2))
layer_test(core.CosineDense,
kwargs={'units': 3},
input_shape=(None, None, 2))
layer_test(core.CosineDense, kwargs={'units': 3}, input_shape=(3, 4, 5, 2))
layer_test(core.CosineDense,
kwargs={
'units': 3,
'kernel_regularizer': regularizers.l2(0.01),
'bias_regularizer': regularizers.l1(0.01),
'activity_regularizer': regularizers.l2(0.01),
'kernel_constraint': constraints.MaxNorm(1),
'bias_constraint': constraints.MaxNorm(1)
},
input_shape=(3, 2))
X = np.random.randn(1, 20)
model = Sequential()
model.add(core.CosineDense(1, use_bias=True, input_shape=(20, )))
model.compile(loss='mse', optimizer='rmsprop')
W = model.get_weights()
W[0] = X.T
W[1] = np.asarray([1.])
model.set_weights(W)
out = model.predict(X)
assert_allclose(out, np.ones((1, 1), dtype=K.floatx()), atol=1e-5)
X = np.random.randn(1, 20)
model = Sequential()
model.add(core.CosineDense(1, use_bias=False, input_shape=(20, )))
model.compile(loss='mse', optimizer='rmsprop')
W = model.get_weights()
W[0] = -2 * X.T
model.set_weights(W)
out = model.predict(X)
assert_allclose(out, -np.ones((1, 1), dtype=K.floatx()), atol=1e-5)
def test_tfoptimizer():
from keras import constraints
from tensorflow import train
optimizer = optimizers.TFOptimizer(train.AdamOptimizer())
model = Sequential()
model.add(Dense(num_classes, input_shape=(3,), kernel_constraint=constraints.MaxNorm(1)))
model.compile(loss='mean_squared_error', optimizer=optimizer)
model.fit(np.random.random((5, 3)), np.random.random((5, num_classes)),
epochs=1, batch_size=5, verbose=0)
# not supported
with pytest.raises(NotImplementedError):
optimizer.weights
with pytest.raises(NotImplementedError):
optimizer.get_config()
with pytest.raises(NotImplementedError):
optimizer.from_config(None)
