def __init__(self,
feat_level,
target_num_channels,
apply_bn=False,
is_training_bn=None,
conv_after_downsample=False,
strategy=None,
data_format=None,
pooling_type=None,
upsampling_type=None,
model_optimizations=None,
name='resample_p0'):
super().__init__(name=name)
self.apply_bn = apply_bn
self.is_training_bn = is_training_bn
self.data_format = data_format
self.target_num_channels = target_num_channels
self.feat_level = feat_level
self.strategy = strategy
self.conv_after_downsample = conv_after_downsample
self.pooling_type = pooling_type or 'max'
self.upsampling_type = upsampling_type or 'nearest'
self.conv2d = tf.keras.layers.Conv2D(self.target_num_channels, (1, 1),
padding='same',
data_format=self.data_format,
name='conv2d')
if model_optimizations:
for method in model_optimizations.keys():
self.conv2d = tfmot.get_method(method)(self.conv2d)
self.bn = util_keras.build_batch_norm(
is_training_bn=self.is_training_bn,
data_format=self.data_format,
strategy=self.strategy,
name='bn')
def __init__(self,
is_training_bn,
conv_bn_act_pattern,
separable_conv,
fpn_num_filters,
act_type,
data_format,
strategy,
model_optimizations,
name='op_after_combine'):
super().__init__(name=name)
self.conv_bn_act_pattern = conv_bn_act_pattern
self.separable_conv = separable_conv
self.fpn_num_filters = fpn_num_filters
self.act_type = act_type
self.data_format = data_format
self.strategy = strategy
self.is_training_bn = is_training_bn
if self.separable_conv:
conv2d_layer = functools.partial(
tf.keras.layers.SeparableConv2D, depth_multiplier=1)
else:
conv2d_layer = tf.keras.layers.Conv2D
self.conv_op = conv2d_layer(
filters=fpn_num_filters,
kernel_size=(3, 3),
padding='same',
use_bias=not self.conv_bn_act_pattern,
data_format=self.data_format,
name='conv')
if model_optimizations:
for method in model_optimizations.keys():
self.conv_op = (
tfmot.get_method(method)(self.conv_op))
self.bn = util_keras.build_batch_norm(
is_training_bn=self.is_training_bn,
data_format=self.data_format,
strategy=self.strategy,
name='bn')