def testAtrousFullyConvolutionalValues(self):
"""Verify dense feature extraction with atrous convolution."""
nominal_stride = 32
for output_stride in [4, 8, 16, 32, None]:
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
with tf.Graph().as_default():
with self.test_session() as sess:
tf.set_random_seed(0)
inputs = create_test_input(2, 81, 81, 3)
# Dense feature extraction followed by subsampling.
output, _ = self._resnet_small(
inputs,
None,
is_training=False,
global_pool=False,
output_stride=output_stride)
if output_stride is None:
factor = 1
else:
factor = nominal_stride // output_stride
output = resnet_utils.subsample(output, factor)
# Make the two networks use the same weights.
tf.get_variable_scope().reuse_variables()
# Feature extraction at the nominal network rate.
expected, _ = self._resnet_small(inputs,
None,
is_training=False,
global_pool=False)
sess.run(tf.global_variables_initializer())
self.assertAllClose(output.eval(),
expected.eval(),
atol=1e-4,
rtol=1e-4)
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name (unused).
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
with tf.variable_scope(self._architecture, reuse=self._reuse_weights):
with slim.arg_scope(
resnet_utils.resnet_arg_scope(
batch_norm_epsilon=1e-5,
batch_norm_scale=True,
weight_decay=self._weight_decay)):
with slim.arg_scope([slim.batch_norm],
is_training=self._train_batch_norm):
blocks = [
resnet_utils.Block('block4', resnet_v1.bottleneck,
[{
'depth': 2048,
'depth_bottleneck': 512,
'stride': 1
}] * 3)
]
proposal_classifier_features = resnet_utils.stack_blocks_dense(
proposal_feature_maps, blocks)
return proposal_classifier_features
def testEndpointNames(self):
# Like ResnetUtilsTest.testEndPointsV2(), but for the public API.
global_pool = True
num_classes = 10
inputs = create_test_input(2, 224, 224, 3)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = self._resnet_small(inputs,
num_classes,
global_pool=global_pool,
scope='resnet')
expected = ['resnet/conv1']
for block in range(1, 5):
for unit in range(1, 4 if block < 4 else 3):
for conv in range(1, 4):
expected.append(
'resnet/block%d/unit_%d/bottleneck_v2/conv%d' %
(block, unit, conv))
expected.append('resnet/block%d/unit_%d/bottleneck_v2' %
(block, unit))
expected.append('resnet/block%d/unit_1/bottleneck_v2/shortcut' %
block)
expected.append('resnet/block%d' % block)
expected.extend([
'global_pool', 'resnet/logits', 'resnet/spatial_squeeze',
'predictions'
])
self.assertItemsEqual(end_points.keys(), expected)
def testEndPointsV2(self):
"""Test the end points of a tiny v2 bottleneck network."""
blocks = [
resnet_v2.resnet_v2_block('block1',
base_depth=1,
num_units=2,
stride=2),
resnet_v2.resnet_v2_block('block2',
base_depth=2,
num_units=2,
stride=1),
]
inputs = create_test_input(2, 32, 16, 3)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = self._resnet_plain(inputs, blocks, scope='tiny')
expected = [
'tiny/block1/unit_1/bottleneck_v2/shortcut',
'tiny/block1/unit_1/bottleneck_v2/conv1',
'tiny/block1/unit_1/bottleneck_v2/conv2',
'tiny/block1/unit_1/bottleneck_v2/conv3',
'tiny/block1/unit_2/bottleneck_v2/conv1',
'tiny/block1/unit_2/bottleneck_v2/conv2',
'tiny/block1/unit_2/bottleneck_v2/conv3',
'tiny/block2/unit_1/bottleneck_v2/shortcut',
'tiny/block2/unit_1/bottleneck_v2/conv1',
'tiny/block2/unit_1/bottleneck_v2/conv2',
'tiny/block2/unit_1/bottleneck_v2/conv3',
'tiny/block2/unit_2/bottleneck_v2/conv1',
'tiny/block2/unit_2/bottleneck_v2/conv2',
'tiny/block2/unit_2/bottleneck_v2/conv3'
]
self.assertItemsEqual(expected, end_points.keys())
def _extract_proposal_features(self, preprocessed_inputs, scope):
"""Extracts first stage RPN features.
Args:
preprocessed_inputs: A [batch, height, width, channels] float32 tensor
representing a batch of images.
scope: A scope name.
Returns:
rpn_feature_map: A tensor with shape [batch, height, width, depth]
activations: A dictionary mapping feature extractor tensor names to
tensors
Raises:
InvalidArgumentError: If the spatial size of `preprocessed_inputs`
(height or width) is less than 33.
ValueError: If the created network is missing the required activation.
"""
if len(preprocessed_inputs.get_shape().as_list()) != 4:
raise ValueError(
'`preprocessed_inputs` must be 4 dimensional, got a '
'tensor of shape %s' % preprocessed_inputs.get_shape())
shape_assert = tf.Assert(
tf.logical_and(
tf.greater_equal(tf.shape(preprocessed_inputs)[1], 33),
tf.greater_equal(tf.shape(preprocessed_inputs)[2], 33)),
['image size must at least be 33 in both height and width.'])
with tf.control_dependencies([shape_assert]):
# Disables batchnorm for fine-tuning with smaller batch sizes.
# TODO(chensun): Figure out if it is needed when image
# batch size is bigger.
with slim.arg_scope(
resnet_utils.resnet_arg_scope(
batch_norm_epsilon=1e-5,
batch_norm_scale=True,
weight_decay=self._weight_decay)):
with tf.variable_scope(self._architecture,
reuse=self._reuse_weights) as var_scope:
_, activations = self._resnet_model(
preprocessed_inputs,
num_classes=None,
is_training=self._train_batch_norm,
global_pool=False,
output_stride=self._first_stage_features_stride,
spatial_squeeze=False,
scope=var_scope)
handle = scope + '/%s/block3' % self._architecture
return activations[handle], activations
def testFullyConvolutionalUnknownHeightWidth(self):
batch = 2
height, width = 65, 65
global_pool = False
inputs = create_test_input(batch, None, None, 3)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
output, _ = self._resnet_small(inputs,
None,
global_pool=global_pool)
self.assertListEqual(output.get_shape().as_list(),
[batch, None, None, 32])
images = create_test_input(batch, height, width, 3)
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(output, {inputs: images.eval()})
self.assertEqual(output.shape, (batch, 3, 3, 32))
def testAtrousValuesBottleneck(self):
"""Verify the values of dense feature extraction by atrous convolution.
Make sure that dense feature extraction by stack_blocks_dense() followed by
subsampling gives identical results to feature extraction at the nominal
network output stride using the simple self._stack_blocks_nondense() above.
"""
block = resnet_v2.resnet_v2_block
blocks = [
block('block1', base_depth=1, num_units=2, stride=2),
block('block2', base_depth=2, num_units=2, stride=2),
block('block3', base_depth=4, num_units=2, stride=2),
block('block4', base_depth=8, num_units=2, stride=1),
]
nominal_stride = 8
# Test both odd and even input dimensions.
height = 30
width = 31
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
with slim.arg_scope([slim.batch_norm], is_training=False):
for output_stride in [1, 2, 4, 8, None]:
with tf.Graph().as_default():
with self.test_session() as sess:
tf.set_random_seed(0)
inputs = create_test_input(1, height, width, 3)
# Dense feature extraction followed by subsampling.
output = resnet_utils.stack_blocks_dense(
inputs, blocks, output_stride)
if output_stride is None:
factor = 1
else:
factor = nominal_stride // output_stride
output = resnet_utils.subsample(output, factor)
# Make the two networks use the same weights.
tf.get_variable_scope().reuse_variables()
# Feature extraction at the nominal network rate.
expected = self._stack_blocks_nondense(
inputs, blocks)
sess.run(tf.global_variables_initializer())
output, expected = sess.run([output, expected])
self.assertAllClose(output,
expected,
atol=1e-4,
rtol=1e-4)
def testClassificationShapes(self):
global_pool = True
num_classes = 10
inputs = create_test_input(2, 224, 224, 3)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = self._resnet_small(inputs,
num_classes,
global_pool=global_pool,
scope='resnet')
endpoint_to_shape = {
'resnet/block1': [2, 28, 28, 4],
'resnet/block2': [2, 14, 14, 8],
'resnet/block3': [2, 7, 7, 16],
'resnet/block4': [2, 7, 7, 32]
}
for endpoint in endpoint_to_shape:
shape = endpoint_to_shape[endpoint]
self.assertListEqual(
end_points[endpoint].get_shape().as_list(), shape)
def testClassificationEndPoints(self):
global_pool = True
num_classes = 10
inputs = create_test_input(2, 224, 224, 3)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
logits, end_points = self._resnet_small(inputs,
num_classes,
global_pool=global_pool,
spatial_squeeze=False,
scope='resnet')
self.assertTrue(logits.op.name.startswith('resnet/logits'))
self.assertListEqual(logits.get_shape().as_list(),
[2, 1, 1, num_classes])
self.assertTrue('predictions' in end_points)
self.assertListEqual(end_points['predictions'].get_shape().as_list(),
[2, 1, 1, num_classes])
self.assertTrue('global_pool' in end_points)
self.assertListEqual(end_points['global_pool'].get_shape().as_list(),
[2, 1, 1, 32])
def testUnknownBatchSize(self):
batch = 2
height, width = 65, 65
global_pool = True
num_classes = 10
inputs = create_test_input(None, height, width, 3)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
logits, _ = self._resnet_small(inputs,
num_classes,
global_pool=global_pool,
spatial_squeeze=False,
scope='resnet')
self.assertTrue(logits.op.name.startswith('resnet/logits'))
self.assertListEqual(logits.get_shape().as_list(),
[None, 1, 1, num_classes])
images = create_test_input(batch, height, width, 3)
with self.test_session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(logits, {inputs: images.eval()})
self.assertEqual(output.shape, (batch, 1, 1, num_classes))
def testFullyConvolutionalEndpointShapes(self):
global_pool = False
num_classes = 10
inputs = create_test_input(2, 321, 321, 3)
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = self._resnet_small(inputs,
num_classes,
global_pool=global_pool,
spatial_squeeze=False,
scope='resnet')
endpoint_to_shape = {
'resnet/block1': [2, 41, 41, 4],
'resnet/block2': [2, 21, 21, 8],
'resnet/block3': [2, 11, 11, 16],
'resnet/block4': [2, 11, 11, 32]
}
for endpoint in endpoint_to_shape:
shape = endpoint_to_shape[endpoint]
self.assertListEqual(
end_points[endpoint].get_shape().as_list(), shape)
def testStridingLastUnitVsSubsampleBlockEnd(self):
"""Compares subsampling at the block's last unit or block's end.
Makes sure that the final output is the same when we use a stride at the
last unit of a block vs. we subsample activations at the end of a block.
"""
block = resnet_v1.resnet_v1_block
blocks = [
block('block1', base_depth=1, num_units=2, stride=2),
block('block2', base_depth=2, num_units=2, stride=2),
block('block3', base_depth=4, num_units=2, stride=2),
block('block4', base_depth=8, num_units=2, stride=1),
]
# Test both odd and even input dimensions.
height = 30
width = 31
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
with slim.arg_scope([slim.batch_norm], is_training=False):
for output_stride in [1, 2, 4, 8, None]:
with tf.Graph().as_default():
with self.test_session() as sess:
tf.set_random_seed(0)
inputs = create_test_input(1, height, width, 3)
# Subsampling at the last unit of the block.
output = resnet_utils.stack_blocks_dense(
inputs,
blocks,
output_stride,
store_non_strided_activations=False,
outputs_collections='output')
output_end_points = slim.utils.convert_collection_to_dict(
'output')
# Make the two networks use the same weights.
tf.get_variable_scope().reuse_variables()
# Subsample activations at the end of the blocks.
expected = resnet_utils.stack_blocks_dense(
inputs,
blocks,
output_stride,
store_non_strided_activations=True,
outputs_collections='expected')
expected_end_points = slim.utils.convert_collection_to_dict(
'expected')
sess.run(tf.global_variables_initializer())
# Make sure that the final output is the same.
output, expected = sess.run([output, expected])
self.assertAllClose(output,
expected,
atol=1e-4,
rtol=1e-4)
# Make sure that intermediate block activations in
# output_end_points are subsampled versions of the corresponding
# ones in expected_end_points.
for i, block in enumerate(blocks[:-1:]):
output = output_end_points[block.scope]
expected = expected_end_points[block.scope]
atrous_activated = (output_stride is not None
and 2**i >= output_stride)
if not atrous_activated:
expected = resnet_utils.subsample(
expected, 2)
output, expected = sess.run([output, expected])
self.assertAllClose(output,
expected,
atol=1e-4,
rtol=1e-4)
