def __init__(self, name, inputs, n_features, tower_setup, old_order=False, filter_size=(3, 3),
strides=(1, 1), dilation=None, pool_size=(1, 1), pool_strides=None, activation="relu", dropout=0.0,
batch_norm=False, bias=False, batch_norm_decay=BATCH_NORM_DECAY_DEFAULT, l2=L2_DEFAULT):
super(Conv, self).__init__()
# mind the order of dropout, conv, activation and batchnorm!
# default: batchnorm -> activation -> dropout -> conv -> pool
# if old_order: dropout -> conv -> batchnorm -> activation -> pool
curr, n_features_inp = prepare_input(inputs)
filter_size = list(filter_size)
strides = list(strides)
pool_size = list(pool_size)
if pool_strides is None:
pool_strides = pool_size
with tf.variable_scope(name):
W = self.create_weight_variable("W", filter_size + [n_features_inp, n_features], l2, tower_setup)
b = None
if bias:
b = self.create_bias_variable("b", [n_features], tower_setup)
if old_order:
curr = apply_dropout(curr, dropout)
if dilation is None:
curr = conv2d(curr, W, strides)
else:
curr = conv2d_dilated(curr, W, dilation)
if bias:
curr += b
if batch_norm:
curr = self.create_and_apply_batch_norm(curr, n_features, batch_norm_decay, tower_setup)
curr = get_activation(activation)(curr)
else:
if batch_norm:
curr = self.create_and_apply_batch_norm(curr, n_features_inp, batch_norm_decay, tower_setup)
curr = get_activation(activation)(curr)
curr = apply_dropout(curr, dropout)
if dilation is None:
curr = conv2d(curr, W, strides)
else:
curr = conv2d_dilated(curr, W, dilation)
if bias:
curr += b
if pool_size != [1, 1]:
curr = max_pool(curr, pool_size, pool_strides)
self.outputs = [curr]
def __init__(self, name, inputs, targets, n_classes, void_label, tower_setup, filter_size=(1, 1),
input_activation=None, dilation=None, resize_targets=False, resize_logits=False, loss="ce",
fraction=None, l2=L2_DEFAULT, dropout=0.0):
super(SegmentationSoftmax, self).__init__()
assert targets.get_shape().ndims == 4, targets.get_shape()
assert not (resize_targets and resize_logits)
inp, n_features_inp = prepare_input(inputs)
filter_size = list(filter_size)
with tf.variable_scope(name):
if input_activation is not None:
inp = get_activation(input_activation)(inp)
inp = apply_dropout(inp, dropout)
self.W, self.b, self.W_adjustable, self.b_adjustable, self.n_classes_current, W, b = self.create_weights(
n_classes, filter_size, n_features_inp, l2, tower_setup)
self.adjustable_output_assign_data = self._create_adjustable_output_assign_data(tower_setup)
if self.n_classes_current is None:
self.n_classes_current = n_classes
if dilation is None:
y_pred = conv2d(inp, W) + b
else:
y_pred = conv2d_dilated(inp, W, dilation) + b
self.outputs = [tf.nn.softmax(y_pred, -1, 'softmax')]
if resize_targets:
targets = tf.image.resize_nearest_neighbor(targets, tf.shape(y_pred)[1:3])
if resize_logits:
y_pred = tf.image.resize_images(y_pred, tf.shape(targets)[1:3])
pred = tf.argmax(y_pred, axis=3)
targets = tf.cast(targets, tf.int64)
targets = tf.squeeze(targets, axis=3)
# TODO: Void label is not considered in the iou calculation.
if void_label is not None:
# avoid nan by replacing void label by 0
# note: the loss for these cases is multiplied by 0 below
void_label_mask = tf.equal(targets, void_label)
no_void_label_mask = tf.logical_not(void_label_mask)
targets = tf.where(void_label_mask, tf.zeros_like(targets), targets)
else:
no_void_label_mask = None
self.measures = self.create_measures(n_classes, pred, targets)
self.loss = self.create_loss(loss, fraction, no_void_label_mask, targets, tower_setup, void_label, y_pred)
self.add_scalar_summary(self.loss, "loss")