def testConv(self):
if 'GPU' in self.device:
# TODO(b/32333178)
self.skipTest(
'Current implementation of RandomStandardNormal kernel '
'is very slow on GPU, and has been blacklisted.')
with self.test_scope():
data_format = 'channels_last'
conv = convolutional.Conv2D(
filters=1,
kernel_size=2,
padding='VALID',
data_format=data_format,
activation=nn_ops.relu,
kernel_initializer=init_ops.ones_initializer(),
bias_initializer=init_ops.zeros_initializer())
pool = pooling.MaxPooling2D(2, 2, data_format=data_format)
def model(x):
x = conv(x)
return pool(x)
model = function.defun(model)
x = array_ops.ones([1, 4, 4, 1])
y = model(x)
self.assertAllEqual(y.numpy(), [[[[4.]]]])
def testMaxPooling2DPaddingSame(self):
height, width = 7, 9
images = random_ops.random_uniform((5, height, width, 4), seed=1)
layer = pooling_layers.MaxPooling2D(
images.get_shape()[1:3], strides=2, padding='same')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(), [5, 4, 5, 4])
def testCreateMaxPooling2DChannelsFirst(self):
height, width = 7, 9
images = random_ops.random_uniform((5, 2, height, width))
layer = pooling_layers.MaxPooling2D([2, 2],
strides=1,
data_format='channels_first')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(), [5, 2, 6, 8])
def testCreatePooling2DWithStrides(self):
height, width = 6, 8
# Test strides tuple
images = random_ops.random_uniform((5, height, width, 3), seed=1)
layer = pooling_layers.MaxPooling2D([2, 2], strides=(2, 2), padding='same')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(),
[5, height / 2, width / 2, 3])
# Test strides integer
layer = pooling_layers.MaxPooling2D([2, 2], strides=2, padding='same')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(),
[5, height / 2, width / 2, 3])
# Test unequal strides
layer = pooling_layers.MaxPooling2D([2, 2], strides=(2, 1), padding='same')
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(),
[5, height / 2, width, 3])
def testCreateMaxPooling2D(self):
height, width = 7, 9
images = random_ops.random_uniform((5, height, width, 4))
layer = pooling_layers.MaxPooling2D([2, 2], strides=2)
output = layer.apply(images)
self.assertListEqual(output.get_shape().as_list(), [5, 3, 4, 4])
