def test_custom_conv2d_passes_custom_layer_options(self,
mock_custom_layer_impl):
x = tf.constant(
[[[[1, 2, 3], [4, 5, 6]], [[7, 8, 9], [10, 11, 12]]],
[[[0, 0, 0], [-1, -2, -3]], [[1, -2, 2], [2, 5, 3]]]],
dtype=tf.float32)
layers.custom_conv2d(x, 1, 2)
mock_custom_layer_impl.assert_called_once_with(
mock.ANY,
kernel_shape=[2, 2, 3, 1],
bias_shape=(1,),
activation=None,
he_initializer_slope=1.0,
use_weight_scaling=True)
def test_custom_conv2d_passes_conv2d_options(self, mock_conv2d):
x = tf.constant(
[[[[1, 2, 3], [4, 5, 6]], [[7, 8, 9], [10, 11, 12]]],
[[[0, 0, 0], [-1, -2, -3]], [[1, -2, 2], [2, 5, 3]]]],
dtype=tf.float32)
layers.custom_conv2d(x, 1, 2)
mock_conv2d.assert_called_once_with(
x,
filters=1,
kernel_size=[2, 2],
strides=(1, 1),
padding='SAME',
use_bias=False,
kernel_initializer=mock.ANY)
def _to_rgb(x):
return layers.custom_conv2d(x=x,
filters=colors,
kernel_size=1,
padding='SAME',
activation=to_rgb_activation,
scope='to_rgb')
def _conv2d(scope, x, kernel_size, filters, padding='SAME'):
return layers.custom_conv2d(x=x,
filters=filters,
kernel_size=kernel_size,
padding=padding,
activation=tf.nn.leaky_relu,
he_initializer_slope=0.0,
scope=scope)
def _to_rgb(x):
return layers.custom_conv2d(
x=x,
filters=colors,
kernel_size=1,
padding='SAME',
activation=to_rgb_activation,
scope='to_rgb')
def _conv2d(scope, x, kernel_size, filters, padding='SAME'):
return layers.custom_conv2d(
x=x,
filters=filters,
kernel_size=kernel_size,
padding=padding,
activation=tf.nn.leaky_relu,
he_initializer_slope=0.0,
scope=scope)
def test_custom_conv2d_list_kernel_size(self, mock_zeros_initializer,
mock_random_normal_initializer):
mock_zeros_initializer.return_value = tf.constant_initializer(1.0)
mock_random_normal_initializer.return_value = tf.constant_initializer(3.0)
x = tf.constant(
[[[[1, 2, 3], [4, 5, 6]], [[7, 8, 9], [10, 11, 12]]],
[[[0, 0, 0], [-1, -2, -3]], [[1, -2, 2], [2, 5, 3]]]],
dtype=tf.float32)
output = layers.custom_conv2d(x, 1, [2, 3])
with self.test_session(use_gpu=True) as sess:
sess.run(tf.global_variables_initializer())
output_np = sess.run(output)
expected_np = [[
[[56.15432739], [56.15432739]],
[[41.30508804], [41.30508804]],
], [[[4.53553391], [4.53553391]], [[8.7781744], [8.7781744]]]]
self.assertNDArrayNear(output_np, expected_np, 1.0e-5)
def test_custom_conv2d_scalar_kernel_size(self, mock_zeros_initializer,
mock_random_normal_initializer):
mock_zeros_initializer.return_value = tf.constant_initializer(1.0)
mock_random_normal_initializer.return_value = tf.constant_initializer(3.0)
x = tf.constant(
[[[[1, 2, 3], [4, 5, 6]], [[7, 8, 9], [10, 11, 12]]],
[[[0, 0, 0], [-1, -2, -3]], [[1, -2, 2], [2, 5, 3]]]],
dtype=tf.float32)
output = layers.custom_conv2d(x, 1, 2)
with self.test_session(use_gpu=True) as sess:
sess.run(tf.global_variables_initializer())
output_np = sess.run(output)
expected_np = [[[[68.54998016], [42.56921768]], [[50.36344528],
[29.57883835]]],
[[[5.33012676], [4.46410179]], [[10.52627945],
[9.66025352]]]]
self.assertNDArrayNear(output_np, expected_np, 1.0e-5)
