def test_fit_octave(self):
inputs = keras.layers.Input(shape=(32, 3))
high, low = OctaveConv1D(13, kernel_size=3, octave=4)(inputs)
high, low = keras.layers.MaxPool1D()(high), keras.layers.MaxPool1D()(low)
conv = OctaveConv1D(5, kernel_size=3, octave=4, ratio_out=0.0)([high, low])
flatten = keras.layers.Flatten()(conv)
outputs = keras.layers.Dense(units=2, activation='softmax')(flatten)
model = keras.models.Model(inputs=inputs, outputs=outputs)
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
model.summary(line_length=200)
self._test_fit(model)
def test_raise_dimension_specified(self):
with self.assertRaises(ValueError):
inputs = keras.layers.Input(shape=(32, None))
outputs = OctaveConv1D(13, kernel_size=3, ratio_out=0.0)(inputs)
model = keras.models.Model(inputs=inputs, outputs=outputs)
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
with self.assertRaises(ValueError):
inputs_high = keras.layers.Input(shape=(32, 3))
inputs_low = keras.layers.Input(shape=(32, None))
outputs = OctaveConv1D(13, kernel_size=3, ratio_out=0.0)([inputs_high, inputs_low])
model = keras.models.Model(inputs=[inputs_high, inputs_low], outputs=outputs)
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
def test_make_dual_layer(self):
inputs = Input(shape=(32, 3))
conv = OctaveConv1D(13, kernel_size=3)(inputs)
pool = octave_dual(conv, MaxPool1D())
conv = OctaveConv1D(7, kernel_size=3)(pool)
pool = octave_dual(conv, MaxPool1D())
conv = OctaveConv1D(5, kernel_size=3, ratio_out=0.0)(pool)
flatten = octave_dual(conv, Flatten())
outputs = Dense(units=2, activation='softmax')(flatten)
model = Model(inputs=inputs, outputs=outputs)
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
model.summary(line_length=200)
self._test_fit(model)
def test_fit_lower_output(self):
inputs = Input(shape=(32, 3))
high, low = OctaveConv1D(13, kernel_size=3)(inputs)
high, low = MaxPool1D()(high), MaxPool1D()(low)
high, low = OctaveConv1D(7, kernel_size=3)([high, low])
high, low = MaxPool1D()(high), MaxPool1D()(low)
conv = OctaveConv1D(5, kernel_size=3, ratio_out=1.0)([high, low])
flatten = Flatten()(conv)
outputs = Dense(units=2, activation='softmax')(flatten)
model = Model(inputs=inputs, outputs=outputs)
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
model.summary(line_length=200)
self._test_fit(model)
def test_raise_octave_divisible(self):
with self.assertRaises(ValueError):
inputs = Input(shape=(32, 3))
outputs = OctaveConv1D(13, kernel_size=3, octave=5,
ratio_out=0.0)(inputs)
model = Model(inputs=inputs, outputs=outputs)
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy')