def _maybe_apply_1x1(feat):
"""Apply 1x1 conv to change layer width if necessary."""
if num_channels != target_num_channels:
feat = tf.layers.conv2d(
feat, filters=target_num_channels, kernel_size=(1, 1), padding='same')
if apply_bn:
feat = utils.batch_norm_relu(
feat,
is_training_bn=is_training,
relu=False,
data_format='channels_last',
name='bn')
return feat
def class_net(images,
level,
num_classes,
num_anchors,
num_filters,
is_training,
separable_conv=True,
repeats=4,
survival_prob=None,
use_tpu=False):
"""Class prediction network."""
if separable_conv:
conv_op = functools.partial(
tf.layers.separable_conv2d, depth_multiplier=1,
pointwise_initializer=tf.initializers.variance_scaling(),
depthwise_initializer=tf.initializers.variance_scaling())
else:
conv_op = functools.partial(
tf.layers.conv2d,
kernel_initializer=tf.random_normal_initializer(stddev=0.01))
for i in range(repeats):
orig_images = images
images = conv_op(
images,
num_filters,
kernel_size=3,
bias_initializer=tf.zeros_initializer(),
activation=None,
padding='same',
name='class-%d' % i)
images = utils.batch_norm_relu(
images,
is_training,
relu=True,
init_zero=False,
use_tpu=use_tpu,
name='class-%d-bn-%d' % (i, level))
if i > 0 and survival_prob:
images = utils.drop_connect(images, is_training, survival_prob)
images = images + orig_images
classes = conv_op(
images,
num_classes * num_anchors,
kernel_size=3,
bias_initializer=tf.constant_initializer(-np.log((1 - 0.01) / 0.01)),
padding='same',
name='class-predict')
return classes
def build_bifpn_layer(feats,
feat_sizes,
fpn_name,
fpn_config,
is_training,
fpn_num_filters,
min_level,
max_level,
separable_conv,
apply_bn_for_resampling,
conv_after_downsample,
use_native_resize_op,
conv_bn_relu_pattern,
pooling_type,
use_tpu=False):
"""Builds a feature pyramid given previous feature pyramid and config."""
config = fpn_config or get_fpn_config(fpn_name)
num_output_connections = [0 for _ in feats]
for i, fnode in enumerate(config.nodes):
with tf.variable_scope('fnode{}'.format(i)):
logging.info('fnode %d : %s', i, fnode)
new_node_width = feat_sizes[fnode['width_index']]
nodes = []
for idx, input_offset in enumerate(fnode['inputs_offsets']):
input_node = feats[input_offset]
num_output_connections[input_offset] += 1
input_node = resample_feature_map(
input_node, '{}_{}_{}'.format(idx, input_offset,
len(feats)), new_node_width,
fpn_num_filters, apply_bn_for_resampling, is_training,
conv_after_downsample, use_native_resize_op, pooling_type)
nodes.append(input_node)
# Combine all nodes.
dtype = nodes[0].dtype
if config.weight_method == 'attn':
edge_weights = [
tf.cast(tf.Variable(1.0, name='WSM'), dtype=dtype)
for _ in range(len(fnode['inputs_offsets']))
]
normalized_weights = tf.nn.softmax(tf.stack(edge_weights))
nodes = tf.stack(nodes, axis=-1)
new_node = tf.reduce_sum(
tf.multiply(nodes, normalized_weights), -1)
elif config.weight_method == 'fastattn':
edge_weights = [
tf.nn.relu(
tf.cast(tf.Variable(1.0, name='WSM'), dtype=dtype))
for _ in range(len(fnode['inputs_offsets']))
]
weights_sum = tf.add_n(edge_weights)
nodes = [
nodes[i] * edge_weights[i] / (weights_sum + 0.0001)
for i in range(len(nodes))
]
new_node = tf.add_n(nodes)
elif config.weight_method == 'sum':
new_node = tf.add_n(nodes)
else:
raise ValueError('unknown weight_method {}'.format(
config.weight_method))
with tf.variable_scope('op_after_combine{}'.format(len(feats))):
if not conv_bn_relu_pattern:
new_node = utils.relu_fn(new_node)
if separable_conv:
conv_op = functools.partial(tf.layers.separable_conv2d,
depth_multiplier=1)
else:
conv_op = tf.layers.conv2d
new_node = conv_op(
new_node,
filters=fpn_num_filters,
kernel_size=(3, 3),
padding='same',
use_bias=True if not conv_bn_relu_pattern else False,
name='conv')
new_node = utils.batch_norm_relu(
new_node,
is_training_bn=is_training,
relu=False if not conv_bn_relu_pattern else True,
data_format='channels_last',
use_tpu=use_tpu,
name='bn')
feats.append(new_node)
num_output_connections.append(0)
output_feats = {}
for l in range(min_level, max_level + 1):
for i, fnode in enumerate(reversed(config.nodes)):
if fnode['width_index'] == l:
output_feats[l] = feats[-1 - i]
break
return output_feats
