def resnet_v1_200(inputs,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
reuse=None,
scope='resnet_v1_200'):
"""ResNet-200 model of [2]. See resnet_v1() for arg and return description."""
blocks = [
resnet_utils.Block('block1', bottleneck,
[(256, 64, 1)] * 2 + [(256, 64, 2)]),
resnet_utils.Block('block2', bottleneck,
[(512, 128, 1)] * 23 + [(512, 128, 2)]),
resnet_utils.Block('block3', bottleneck,
[(1024, 256, 1)] * 35 + [(1024, 256, 2)]),
resnet_utils.Block('block4', bottleneck, [(2048, 512, 1)] * 3)
]
return resnet_v1(inputs,
blocks,
num_classes,
is_training,
global_pool=global_pool,
output_stride=output_stride,
include_root_block=True,
reuse=reuse,
scope=scope)
def _resnet_small(self,
inputs,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
include_root_block=True,
reuse=None,
scope='resnet_v1_small'):
"""A shallow and thin ResNet v1 for faster tests."""
bottleneck = resnet_v1.bottleneck
blocks = [
resnet_utils.Block(
'block1', bottleneck, [(4, 1, 1)] * 2 + [(4, 1, 2)]),
resnet_utils.Block(
'block2', bottleneck, [(8, 2, 1)] * 2 + [(8, 2, 2)]),
resnet_utils.Block(
'block3', bottleneck, [(16, 4, 1)] * 2 + [(16, 4, 2)]),
resnet_utils.Block(
'block4', bottleneck, [(32, 8, 1)] * 2)]
return resnet_v1.resnet_v1(inputs, blocks, num_classes,
is_training=is_training,
global_pool=global_pool,
output_stride=output_stride,
include_root_block=include_root_block,
reuse=reuse,
scope=scope)
def testEndPointsV2(self):
"""Test the end points of a tiny v2 bottleneck network."""
bottleneck = resnet_v2.bottleneck
blocks = [
resnet_utils.Block('block1', bottleneck, [(4, 1, 1), (4, 1, 2)]),
resnet_utils.Block('block2', bottleneck, [(8, 2, 1), (8, 2, 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)
def _atrousValues(self, bottleneck):
"""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.
Args:
bottleneck: The bottleneck function.
"""
blocks = [
resnet_utils.Block('block1', bottleneck, [(4, 1, 1), (4, 1, 2)]),
resnet_utils.Block('block2', bottleneck, [(8, 2, 1), (8, 2, 2)]),
resnet_utils.Block('block3', bottleneck, [(16, 4, 1), (16, 4, 2)]),
resnet_utils.Block('block4', bottleneck, [(32, 8, 1), (32, 8, 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 _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 resnet_v2_small_beta_block(scope, base_depth, num_units, stride):
"""helper for resnet v2"""
block_args = []
for _ in range(num_units - 1):
block_args.append({'depth': base_depth, 'stride': 1, 'unit_rate': 1})
block_args.append({'depth': base_depth, 'stride': stride, 'unit_rate': 1})
return resnet_utils.Block(scope, lite_bottleneck_v2, block_args)
def resnet_v1_small_beta_block(scope, base_depth, num_units, stride):
"""Helper function for creating a resnet_18 beta variant bottleneck block.
Args:
scope: The scope of the block.
base_depth: The depth of the bottleneck layer for each unit.
num_units: The number of units in the block.
stride: The stride of the block, implemented as a stride in the last unit.
All other units have stride=1.
Returns:
A resnet_18 bottleneck block.
"""
block_args = []
for _ in range(num_units - 1):
block_args.append({'depth': base_depth, 'stride': 1, 'unit_rate': 1})
block_args.append({'depth': base_depth, 'stride': stride, 'unit_rate': 1})
return resnet_utils.Block(scope, lite_bottleneck, block_args)
def resnet_v1_block(scope, base_depth, num_units, stride):
"""Helper function for creating a resnet_v1 bottleneck block.
Args:
scope: The scope of the block.
base_depth: The depth of the bottleneck layer for each unit.
num_units: The number of units in the block.
stride: The stride of the block, implemented as a stride in the last unit.
All other units have stride=1.
Returns:
A resnet_v1 bottleneck block.
"""
return resnet_utils.Block(scope, bottleneck, [{
'depth': base_depth * 4,
'depth_bottleneck': base_depth,
'stride': 1
}] * (num_units - 1) + [{
'depth': base_depth * 4,
'depth_bottleneck': base_depth,
'stride': stride
}])
def resnet_v1_101_beta(inputs,
num_classes=None,
is_training=None,
global_pool=False,
output_stride=None,
multi_grid=None,
reuse=None,
scope='resnet_v1_101',
sync_batch_norm_method='None'):
"""Resnet v1 101 beta variant.
This variant modifies the first convolution layer of ResNet-v1-101. In
particular, it changes the original one 7x7 convolution to three 3x3
convolutions.
Args:
inputs: A tensor of size [batch, height_in, width_in, channels].
num_classes: Number of predicted classes for classification tasks. If None
we return the features before the logit layer.
is_training: Enable/disable is_training for batch normalization.
global_pool: If True, we perform global average pooling before computing the
logits. Set to True for image classification, False for dense prediction.
output_stride: If None, then the output will be computed at the nominal
network stride. If output_stride is not None, it specifies the requested
ratio of input to output spatial resolution.
multi_grid: Employ a hierarchy of different atrous rates within network.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
sync_batch_norm_method: String, sync batchnorm method.
Returns:
net: A rank-4 tensor of size [batch, height_out, width_out, channels_out].
If global_pool is False, then height_out and width_out are reduced by a
factor of output_stride compared to the respective height_in and width_in,
else both height_out and width_out equal one. If num_classes is None, then
net is the output of the last ResNet block, potentially after global
average pooling. If num_classes is not None, net contains the pre-softmax
activations.
end_points: A dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: if multi_grid is not None and does not have length = 3.
"""
if multi_grid is None:
multi_grid = _DEFAULT_MULTI_GRID
else:
if len(multi_grid) != 3:
raise ValueError('Expect multi_grid to have length 3.')
blocks = [
resnet_v1_beta_block('block1', base_depth=64, num_units=3, stride=2),
resnet_v1_beta_block('block2', base_depth=128, num_units=4, stride=2),
resnet_v1_beta_block('block3', base_depth=256, num_units=23, stride=2),
resnet_utils.Block('block4', bottleneck, [{
'depth': 2048,
'depth_bottleneck': 512,
'stride': 1,
'unit_rate': rate
} for rate in multi_grid]),
]
return resnet_v1_beta(
inputs,
blocks=blocks,
num_classes=num_classes,
is_training=is_training,
global_pool=global_pool,
output_stride=output_stride,
root_block_fn=functools.partial(root_block_fn_for_beta_variant),
reuse=reuse,
scope=scope,
sync_batch_norm_method=sync_batch_norm_method)
def resnet_mod(inputs,
num_classes=None,
is_training=None,
global_pool=False,
output_stride=None,
multi_grid=None,
root_depth_multiplier=0.25,
reuse=None,
scope='resnet_v1_18',
sync_batch_norm_method='None'):
"""
A custom Resnet variant based on v2 preact architecture.
"""
## define the multi_grid/atrous blocks
if multi_grid is None:
multi_grid = [1, 1]
else:
if len(multi_grid) != 2:
raise ValueError('Expect multi_grid to have length 2.')
block4_args = []
for rate in multi_grid:
block4_args.append({'depth': 512, 'stride': 1, 'unit_rate': rate})
blocks = [
resnet_v2_small_beta_block('block1',
base_depth=64,
num_units=1,
stride=2),
resnet_v2_small_beta_block('block2',
base_depth=128,
num_units=1,
stride=2),
resnet_v2_small_beta_block('block3',
base_depth=256,
num_units=1,
stride=2),
resnet_utils.Block('block4', lite_bottleneck_v2, block4_args),
]
# root_block_fn = root_block_fn_for_beta_variant
root_block_fn = functools.partial(conv2d_ws.conv2d_same,
num_outputs=64,
kernel_size=3,
stride=2,
scope='root_conv1')
batch_norm = utils.get_batch_norm_fn(sync_batch_norm_method)
with tf.variable_scope(scope, 'resnet_mod', [inputs], reuse=reuse) as sc:
end_points_collection = sc.original_name_scope + '_end_points'
with slim.arg_scope([
slim.conv2d, conv2d_ws.conv2d, lite_bottleneck_v2,
resnet_utils.stack_blocks_dense
],
outputs_collections=end_points_collection):
if is_training is not None:
arg_scope = slim.arg_scope([batch_norm],
is_training=is_training)
else:
arg_scope = slim.arg_scope([])
with arg_scope:
net = inputs
if output_stride is not None:
if output_stride % 4 != 0:
raise ValueError(
'The output_stride needs to be a multiple of 4.')
output_stride //= 2
net = root_block_fn(net)
# net = slim.max_pool2d(net, 3, stride=2, padding='SAME', scope='pool1')
net = resnet_utils.stack_blocks_dense(net, blocks,
output_stride)
## add a batchnorm and relu layer since the last conv output don't have them in v2
net = slim.batch_norm(net,
activation_fn=tf.nn.relu,
scope='postnorm')
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(
end_points_collection)
return net, end_points
