def testCreateConv2DTransposeWithStrides(self):
height, width = 6, 8
# Test strides tuple
images = random_ops.random_uniform((5, height, width, 3), seed=1)
layer = conv_layers.Conv2DTranspose(32, [3, 3],
strides=(2, 2),
padding='same')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(),
[5, height * 2, width * 2, 32])
# Test strides integer
layer = conv_layers.Conv2DTranspose(32, [3, 3],
strides=2,
padding='same')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(),
[5, height * 2, width * 2, 32])
# Test unequal strides
layer = conv_layers.Conv2DTranspose(32, [3, 3],
strides=(2, 1),
padding='same')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(),
[5, height * 2, width, 32])
def testConv2DTransposePaddingSame(self):
height, width = 7, 9
images = random_ops.random_uniform((5, height, width, 32), seed=1)
layer = conv_layers.Conv2DTranspose(
64, images.get_shape()[1:3], padding='same')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(), [5, height, width, 64])
def testConv2DTransposeBiasRegularizer(self):
height, width = 7, 9
images = random_ops.random_uniform((5, height, width, 4))
reg = lambda x: 0.1 * math_ops.reduce_sum(x)
layer = conv_layers.Conv2DTranspose(32, [3, 3], bias_regularizer=reg)
layer.apply(images)
loss_keys = ops.get_collection(ops.GraphKeys.REGULARIZATION_LOSSES)
self.assertEqual(len(loss_keys), 1)
self.assertListEqual(layer.losses, loss_keys)
def testCreateConv2DTransposeIntegerKernelSize(self):
height, width = 7, 9
images = random_ops.random_uniform((5, height, width, 4))
layer = conv_layers.Conv2DTranspose(32, 3)
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(),
[5, height + 2, width + 2, 32])
self.assertListEqual(layer.kernel.get_shape().as_list(), [3, 3, 32, 4])
self.assertListEqual(layer.bias.get_shape().as_list(), [32])
def testCreateConv2DTransposeChannelsFirst(self):
height, width = 7, 9
images = random_ops.random_uniform((5, 4, height, width))
layer = conv_layers.Conv2DTranspose(32, [3, 3],
data_format='channels_first')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(),
[5, 32, height + 2, width + 2])
self.assertListEqual(layer.kernel.get_shape().as_list(), [3, 3, 32, 4])
self.assertListEqual(layer.bias.get_shape().as_list(), [32])
def testCreateConv2DTranspose(self):
height, width = 7, 9
images = random_ops.random_uniform((5, height, width, 4))
layer = conv_layers.Conv2DTranspose(32, [3, 3], activation=nn_ops.relu)
output = layer.apply(images)
self.assertEqual(output.op.name, 'conv2d_transpose/Relu')
self.assertListEqual(output.get_shape().as_list(),
[5, height + 2, width + 2, 32])
self.assertListEqual(layer.kernel.get_shape().as_list(), [3, 3, 32, 4])
self.assertListEqual(layer.bias.get_shape().as_list(), [32])
def testConstraints(self):
k_constraint = lambda x: x / math_ops.reduce_sum(x)
b_constraint = lambda x: x / math_ops.reduce_max(x)
layer = conv_layers.Conv2DTranspose(2, 3,
kernel_constraint=k_constraint,
bias_constraint=b_constraint)
inputs = random_ops.random_uniform((5, 3, 3, 5), seed=1)
layer(inputs)
self.assertEqual(layer.kernel_constraint, k_constraint)
self.assertEqual(layer.bias_constraint, b_constraint)
