def random_dataset():
x_train = np.complex64(tf.complex(tf.random.uniform([640, 65, 82, 1]), tf.random.uniform([640, 65, 82, 1])))
x_test = np.complex64(tf.complex(tf.random.uniform([200, 65, 82, 1]), tf.random.uniform([200, 65, 82, 1])))
y_train = np.uint8(np.random.randint(5, size=(640, 1)))
y_test = np.uint8(np.random.randint(5, size=(200, 1)))
model = tf.keras.models.Sequential()
model.add(complex_layers.ComplexInput(input_shape=(65, 82, 1))) # Always use ComplexInput at the start
model.add(complex_layers.ComplexConv2D(8, (5, 5), activation='cart_relu'))
model.add(complex_layers.ComplexMaxPooling2D((2, 2)))
model.add(complex_layers.ComplexConv2D(16, (5, 5), activation='cart_relu'))
model.add(complex_layers.ComplexFlatten())
model.add(complex_layers.ComplexDense(256, activation='cart_relu'))
model.add(complex_layers.ComplexDropout(0.1))
model.add(complex_layers.ComplexDense(64, activation='cart_relu'))
model.add(complex_layers.ComplexDropout(0.1))
model.add(complex_layers.ComplexDense(5, activation='convert_to_real_with_abs'))
# An activation that casts to real must be used at the last layer.
# The loss function cannot minimize a complex number
# Compile it
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'],
# run_eagerly=Trutest_regressione
)
model.summary()
# Train and evaluate
history = model.fit(x_train, y_train, epochs=2, validation_data=(x_test, y_test))
test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
def all_layers_model():
"""
Creates a model using all possible layers to assert no layer changes the dtype to real.
"""
input_shape = (4, 28, 28, 3)
x = tf.cast(tf.random.normal(input_shape), tf.complex64)
model = tf.keras.models.Sequential()
model.add(complex_layers.ComplexInput(
input_shape=input_shape[1:])) # Always use ComplexInput at the start
model.add(complex_layers.ComplexConv2D(32, (3, 3), activation='cart_relu'))
model.add(complex_layers.ComplexAvgPooling2D((2, 2)))
model.add(
complex_layers.ComplexConv2D(64, (3, 3), activation='cart_sigmoid'))
model.add(complex_layers.ComplexDropout(0.5))
model.add(complex_layers.ComplexMaxPooling2D((2, 2)))
model.add(complex_layers.ComplexConv2DTranspose(32, (2, 2)))
model.add(complex_layers.ComplexFlatten())
model.add(complex_layers.ComplexDense(64, activation='cart_tanh'))
model.compile(loss=tf.keras.losses.MeanAbsoluteError(),
optimizer='adam',
metrics=['accuracy'])
y = model(x)
assert y.dtype == np.complex64
return model
def test_complex_dropout_output(self):
dropout = layers.ComplexDropout(self.dropout)
x = np.exp(1j *
np.random.uniform(-np.pi, np.pi, size=(1, self.input_dim)))
y = dropout(x, training=True)
self.assertTrue(np.sum(np.real(y.numpy()) == 0.) > 0)
self.assertTrue(np.sum(np.imag(y.numpy()) == 0.) > 0)
self.assertEqual(y.numpy().shape, (1, self.input_dim))
self.assertTrue(
np.issubdtype(y.dtype.as_numpy_dtype, np.complexfloating))
def get_complex_mnist_model():
inputs = complex_layers.complex_input(shape=(28, 28, 1), dtype=np.float32)
flat = complex_layers.ComplexFlatten(input_shape=(28, 28, 1), dtype=np.float32)(inputs)
dense = complex_layers.ComplexDense(128, activation='cart_relu', dtype=np.float32)(flat)
drop = complex_layers.ComplexDropout(rate=0.5)(dense)
out = complex_layers.ComplexDense(10, activation='softmax_real_with_abs', dtype=np.float32)(drop)
complex_model = tf.keras.Model(inputs, out, name="rvnn")
complex_model.compile(
loss='sparse_categorical_crossentropy',
optimizer=tf.keras.optimizers.Adam(0.001),
metrics=['accuracy'],
)
complex_intermediate_model = tf.keras.Model(inputs, drop)
return complex_model, complex_intermediate_model
def dropout():
tf.random.set_seed(0)
layer = complex_layers.ComplexDropout(.2, input_shape=(2, ))
data = np.arange(10).reshape(5, 2).astype(np.float32)
data = tf.complex(data, data)
outputs = layer(data, training=True)
expected_out = np.array([[0. + 0.j, 1.25 + 1.25j],
[2.5 + 2.5j, 3.75 + 3.75j],
[5. + 5.j, 6.25 + 6.25j],
[7.5 + 7.5j, 8.75 + 8.75j],
[10. + 10.j, 0. + 0.j]])
assert np.all(data == layer(data, training=False))
assert np.all(outputs == expected_out)
ds_train, ds_test = get_dataset()
model = tf.keras.models.Sequential([
complex_layers.ComplexFlatten(input_shape=(28, 28, 1),
dtype=np.float32),
complex_layers.ComplexDense(128,
activation='cart_relu',
dtype=np.float32),
complex_layers.ComplexDropout(rate=0.5),
complex_layers.ComplexDense(10,
activation='softmax_real',
dtype=np.float32)
])
model.compile(
loss='sparse_categorical_crossentropy',
optimizer=tf.keras.optimizers.Adam(0.001),
metrics=['accuracy'],
)
model.fit(ds_train,
epochs=1,
validation_data=ds_test,
verbose=False,
shuffle=False)
model.evaluate(ds_test, verbose=False)
def simple_random_example():
tf.random.set_seed(0)
layer = complex_layers.ComplexDropout(.2, input_shape=(2,), seed=0)
data = np.arange(10).reshape(5, 2).astype(np.float32)
data = tf.complex(data, data)
outputs = layer(data, training=True)
expected_out = np.array([[0. + 0.j, 0. + 0.j],
[0. + 0.j, 3.75 + 3.75j],
[5. + 5.j, 6.25 + 6.25j],
[7.5 + 7.5j, 8.75 + 8.75j],
[10. + 10.j, 11.25 + 11.25j]])
assert np.all(data == layer(data, training=False))
assert np.all(outputs == expected_out)
tf.random.set_seed(0)
layer = tf.keras.layers.Dropout(.2, input_shape=(2,), seed=0)
real_outputs = layer(tf.math.real(data), training=True)
assert np.all(real_outputs == tf.math.real(outputs))