def test_pooling_late_shape_init(self):
network = layers.join(
layers.AveragePooling((2, 2)),
layers.Softmax(),
)
self.assertShapesEqual(network.output_shape, (None, None, None, None))
network = layers.join(layers.Input((10, 10, 1)), network)
self.assertShapesEqual(network.output_shape, (None, 5, 5, 1))
def test_failed_pooling_connection(self):
network = layers.join(
layers.Relu(),
layers.AveragePooling((2, 2)),
layers.Reshape(),
)
error_message = ("Pooling layer expects an input with 4 "
"dimensions, got 2 with shape \(\?, 10\)")
with self.assertRaisesRegexp(LayerConnectionError, error_message):
layers.join(layers.Input(10), network)
def test_average_pooling(self):
input_data = asfloat(
np.array([
[1, 2, 3, -1],
[4, -6, 3, 1],
[0, 0, 1, 0],
[0, -1, 0, 0],
])).reshape(1, 4, 4, 1)
expected_output = asfloat(
np.array([
[1 / 4., 6 / 4.],
[-1 / 4., 1 / 4.],
])).reshape(1, 2, 2, 1)
average_pool_layer = layers.AveragePooling((2, 2))
actual_output = self.eval(average_pool_layer.output(input_data))
np.testing.assert_array_almost_equal(actual_output, expected_output)
def Inception_1(conv_filters):
return layers.join(
[[
ConvReluBN((conv_filters[0][0], 1, 1)),
], [
ConvReluBN((conv_filters[1][0], 1, 1)),
ConvReluBN((conv_filters[1][1], 5, 5), padding=2),
], [
ConvReluBN((conv_filters[2][0], 1, 1)),
ConvReluBN((conv_filters[2][1], 3, 3), padding=1),
ConvReluBN((conv_filters[2][2], 3, 3), padding=1),
], [
layers.AveragePooling((3, 3), stride=(1, 1), padding=1,
mode='exclude_padding'),
ConvReluBN((conv_filters[3][0], 1, 1)),
]],
layers.Concatenate(),
)
def test_average_pooling(self):
X = asfloat(np.array([
[1, 2, 3, -1],
[4, -6, 3, 1],
[0, 0, 1, 0],
[0, -1, 0, 0],
])).reshape(1, 4, 4, 1)
expected_output = asfloat(np.array([
[1 / 4., 6 / 4.],
[-1 / 4., 1 / 4.],
])).reshape(1, 2, 2, 1)
network = layers.join(
layers.Input((4, 4, 1)),
layers.AveragePooling((2, 2)),
)
actual_output = self.eval(network.output(X))
np.testing.assert_array_almost_equal(actual_output, expected_output)