def call(self, new_node, training):
if not self.conv_bn_act_pattern:
new_node = activation_builder.activation_fn(new_node, self.act_type)
new_node = self.conv_op(new_node)
new_node = self.bn(new_node, training=training)
if self.conv_bn_act_pattern:
new_node = activation_builder.activation_fn(new_node, self.act_type)
return new_node
def call(self, feats, training):
x = feats[-1]
skips = list(reversed(feats[:-1]))
for con2d_t, con2d_t_bn, skip in zip(self.con2d_ts, self.con2d_t_bns,
skips):
x = con2d_t(x)
x = con2d_t_bn(x, training)
x = activation_builder.activation_fn(x, self.act_type)
x = tf.concat([x, skip], axis=-1)
# This is the last layer of the model
return self.head_transpose(x) # 64x64 -> 128x128
def batch_norm_act(inputs,
is_training_bn: bool,
act_type: Union[Text, None],
init_zero: bool = False,
data_format: Text = 'channels_last',
momentum: float = 0.99,
epsilon: float = 1e-3,
name: Text = None):
"""Performs a batch normalization followed by a non-linear activation.
Args:
inputs: `Tensor` of shape `[batch, channels, ...]`.
is_training_bn: `bool` for whether the model is training.
act_type: non-linear relu function type. If None, omits the relu operation.
init_zero: `bool` if True, initializes scale parameter of batch
normalization with 0 instead of 1 (default).
data_format: `str` either "channels_first" for `[batch, channels, height,
width]` or "channels_last for `[batch, height, width, channels]`.
momentum: `float`, momentume of batch norm.
epsilon: `float`, small value for numerical stability.
name: the name of the batch normalization layer
Returns:
A normalized `Tensor` with the same `data_format`.
"""
if init_zero:
gamma_initializer = tf.zeros_initializer()
else:
gamma_initializer = tf.ones_initializer()
if data_format == 'channels_first':
axis = 1
else:
axis = 3
inputs = batch_normalization(inputs=inputs,
axis=axis,
momentum=momentum,
epsilon=epsilon,
center=True,
scale=True,
training=is_training_bn,
gamma_initializer=gamma_initializer,
name=name)
if act_type:
inputs = activation_builder.activation_fn(inputs, act_type)
return inputs
def call(self, inputs, training):
"""Call boxnet."""
box_outputs = []
for level_id in range(0, self.max_level - self.min_level + 1):
image = inputs[level_id]
for i in range(self.repeats):
original_image = image
image = self.conv_ops[i](image)
image = self.bns[i][level_id](image, training=training)
if self.act_type:
image = activation_builder.activation_fn(image, self.act_type)
if i > 0 and self.survival_prob:
image = model_utils.drop_connect(image, training, self.survival_prob)
image = image + original_image
box_outputs.append(self.boxes(image))
return box_outputs