def graph_fn(image_features):
box_prediction_head = keras_box_head.WeightSharedConvolutionalBoxHead(
box_code_size=box_code_size,
conv_hyperparams=self._build_conv_hyperparams(),
num_predictions_per_location=num_predictions_per_location)
class_prediction_head = keras_class_head.WeightSharedConvolutionalClassHead(
num_class_slots=num_classes_without_background + 1,
conv_hyperparams=self._build_conv_hyperparams(),
num_predictions_per_location=num_predictions_per_location)
other_heads = {
other_head_name:
keras_mask_head.WeightSharedConvolutionalMaskHead(
num_classes=num_classes_without_background,
conv_hyperparams=self._build_conv_hyperparams(),
num_predictions_per_location=num_predictions_per_location,
mask_height=mask_height,
mask_width=mask_width)
}
conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor(
is_training=False,
num_classes=num_classes_without_background,
box_prediction_head=box_prediction_head,
class_prediction_head=class_prediction_head,
other_heads=other_heads,
conv_hyperparams=self._build_conv_hyperparams(),
freeze_batchnorm=False,
inplace_batchnorm_update=False,
depth=32,
num_layers_before_predictor=2)
box_predictions = conv_box_predictor([image_features])
for key, value in box_predictions.items():
box_predictions[key] = tf.concat(value, axis=1)
assert len(box_predictions) == 3
return (box_predictions[box_predictor.BOX_ENCODINGS],
box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
box_predictions[other_head_name])
def test_other_heads_predictions(self):
box_code_size = 4
num_classes_without_background = 3
other_head_name = 'Mask'
mask_height = 5
mask_width = 5
num_predictions_per_location = 5
box_prediction_head = keras_box_head.WeightSharedConvolutionalBoxHead(
box_code_size=box_code_size,
conv_hyperparams=self._build_conv_hyperparams(),
num_predictions_per_location=num_predictions_per_location)
class_prediction_head = keras_class_head.WeightSharedConvolutionalClassHead(
num_class_slots=num_classes_without_background + 1,
conv_hyperparams=self._build_conv_hyperparams(),
num_predictions_per_location=num_predictions_per_location)
other_heads = {
other_head_name:
keras_mask_head.WeightSharedConvolutionalMaskHead(
num_classes=num_classes_without_background,
conv_hyperparams=self._build_conv_hyperparams(),
num_predictions_per_location=num_predictions_per_location,
mask_height=mask_height,
mask_width=mask_width)
}
conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor(
is_training=False,
num_classes=num_classes_without_background,
box_prediction_head=box_prediction_head,
class_prediction_head=class_prediction_head,
other_heads=other_heads,
conv_hyperparams=self._build_conv_hyperparams(),
freeze_batchnorm=False,
inplace_batchnorm_update=False,
depth=32,
num_layers_before_predictor=2)
def graph_fn(image_features):
box_predictions = conv_box_predictor([image_features])
for key, value in box_predictions.items():
box_predictions[key] = tf.concat(value, axis=1)
assert len(box_predictions) == 3
return (box_predictions[box_predictor.BOX_ENCODINGS],
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
box_predictions[other_head_name])
batch_size = 4
feature_ht = 8
feature_wt = 8
image_features = np.random.rand(batch_size, feature_ht, feature_wt,
64).astype(np.float32)
(box_encodings, class_predictions, other_head_predictions) = self.execute(
graph_fn, [image_features])
num_anchors = feature_ht * feature_wt * num_predictions_per_location
self.assertAllEqual(box_encodings.shape,
[batch_size, num_anchors, box_code_size])
self.assertAllEqual(
class_predictions.shape,
[batch_size, num_anchors, num_classes_without_background + 1])
self.assertAllEqual(other_head_predictions.shape, [
batch_size, num_anchors, num_classes_without_background, mask_height,
mask_width
])
def build_weight_shared_convolutional_keras_box_predictor(
is_training,
num_classes,
conv_hyperparams,
freeze_batchnorm,
inplace_batchnorm_update,
num_predictions_per_location_list,
depth,
num_layers_before_predictor,
box_code_size,
kernel_size=3,
add_background_class=True,
class_prediction_bias_init=0.0,
use_dropout=False,
dropout_keep_prob=0.8,
share_prediction_tower=False,
apply_batch_norm=True,
use_depthwise=False,
score_converter_fn=tf.identity,
box_encodings_clip_range=None,
name='WeightSharedConvolutionalBoxPredictor'):
"""Builds the Keras WeightSharedConvolutionalBoxPredictor from the arguments.
Args:
is_training: Indicates whether the BoxPredictor is in training mode.
num_classes: number of classes. Note that num_classes *does not*
include the background category, so if groundtruth labels take values
in {0, 1, .., K-1}, num_classes=K (and not K+1, even though the
assigned classification targets can range from {0,... K}).
conv_hyperparams: A `hyperparams_builder.KerasLayerHyperparams` object
containing hyperparameters for convolution ops.
freeze_batchnorm: Whether to freeze batch norm parameters during
training or not. When training with a small batch size (e.g. 1), it is
desirable to freeze batch norm update and use pretrained batch norm
params.
inplace_batchnorm_update: Whether to update batch norm moving average
values inplace. When this is false train op must add a control
dependency on tf.graphkeys.UPDATE_OPS collection in order to update
batch norm statistics.
num_predictions_per_location_list: A list of integers representing the
number of box predictions to be made per spatial location for each
feature map.
depth: depth of conv layers.
num_layers_before_predictor: Number of the additional conv layers before
the predictor.
box_code_size: Size of encoding for each box.
kernel_size: Size of final convolution kernel.
add_background_class: Whether to add an implicit background class.
class_prediction_bias_init: constant value to initialize bias of the last
conv2d layer before class prediction.
use_dropout: Whether to apply dropout to class prediction head.
dropout_keep_prob: Probability of keeping activiations.
share_prediction_tower: Whether to share the multi-layer tower between box
prediction and class prediction heads.
apply_batch_norm: Whether to apply batch normalization to conv layers in
this predictor.
use_depthwise: Whether to use depthwise separable conv2d instead of conv2d.
score_converter_fn: Callable score converter to perform elementwise op on
class scores.
box_encodings_clip_range: Min and max values for clipping the box_encodings.
name: A string name scope to assign to the box predictor. If `None`, Keras
will auto-generate one from the class name.
Returns:
A Keras WeightSharedConvolutionalBoxPredictor class.
"""
if len(set(num_predictions_per_location_list)) > 1:
raise ValueError('num predictions per location must be same for all'
'feature maps, found: {}'.format(
num_predictions_per_location_list))
num_predictions_per_location = num_predictions_per_location_list[0]
box_prediction_head = keras_box_head.WeightSharedConvolutionalBoxHead(
box_code_size=box_code_size,
kernel_size=kernel_size,
conv_hyperparams=conv_hyperparams,
num_predictions_per_location=num_predictions_per_location,
use_depthwise=use_depthwise,
box_encodings_clip_range=box_encodings_clip_range,
name='WeightSharedConvolutionalBoxHead')
class_prediction_head = keras_class_head.WeightSharedConvolutionalClassHead(
num_class_slots=(
num_classes + 1 if add_background_class else num_classes),
use_dropout=use_dropout,
dropout_keep_prob=dropout_keep_prob,
kernel_size=kernel_size,
conv_hyperparams=conv_hyperparams,
num_predictions_per_location=num_predictions_per_location,
class_prediction_bias_init=class_prediction_bias_init,
use_depthwise=use_depthwise,
score_converter_fn=score_converter_fn,
name='WeightSharedConvolutionalClassHead')
other_heads = {}
return (
convolutional_keras_box_predictor.WeightSharedConvolutionalBoxPredictor(
is_training=is_training,
num_classes=num_classes,
box_prediction_head=box_prediction_head,
class_prediction_head=class_prediction_head,
other_heads=other_heads,
conv_hyperparams=conv_hyperparams,
depth=depth,
num_layers_before_predictor=num_layers_before_predictor,
freeze_batchnorm=freeze_batchnorm,
inplace_batchnorm_update=inplace_batchnorm_update,
kernel_size=kernel_size,
apply_batch_norm=apply_batch_norm,
share_prediction_tower=share_prediction_tower,
use_depthwise=use_depthwise,
name=name))
def build_weight_shared_convolutional_keras_box_predictor(
is_training,
num_classes,
conv_hyperparams,
freeze_batchnorm,
inplace_batchnorm_update,
num_predictions_per_location_list,
depth,
num_layers_before_predictor,
box_code_size,
kernel_size=3,
add_background_class=True,
class_prediction_bias_init=0.0,
use_dropout=False,
dropout_keep_prob=0.8,
share_prediction_tower=False,
apply_batch_norm=True,
use_depthwise=False,
score_converter_fn=tf.identity,
box_encodings_clip_range=None,
name='WeightSharedConvolutionalBoxPredictor'):
if len(set(num_predictions_per_location_list)) > 1:
raise ValueError('num predictions per location must be same for all'
'feature maps, found: {}'.format(
num_predictions_per_location_list))
num_predictions_per_location = num_predictions_per_location_list[0]
box_prediction_head = keras_box_head.WeightSharedConvolutionalBoxHead(
box_code_size=box_code_size,
kernel_size=kernel_size,
conv_hyperparams=conv_hyperparams,
num_predictions_per_location=num_predictions_per_location,
use_depthwise=use_depthwise,
box_encodings_clip_range=box_encodings_clip_range,
name='WeightSharedConvolutionalBoxHead')
class_prediction_head = keras_class_head.WeightSharedConvolutionalClassHead(
num_class_slots=(
num_classes + 1 if add_background_class else num_classes),
use_dropout=use_dropout,
dropout_keep_prob=dropout_keep_prob,
kernel_size=kernel_size,
conv_hyperparams=conv_hyperparams,
num_predictions_per_location=num_predictions_per_location,
class_prediction_bias_init=class_prediction_bias_init,
use_depthwise=use_depthwise,
score_converter_fn=score_converter_fn,
name='WeightSharedConvolutionalClassHead')
other_heads = {}
return (
convolutional_keras_box_predictor.WeightSharedConvolutionalBoxPredictor(
is_training=is_training,
num_classes=num_classes,
box_prediction_head=box_prediction_head,
class_prediction_head=class_prediction_head,
other_heads=other_heads,
conv_hyperparams=conv_hyperparams,
depth=depth,
num_layers_before_predictor=num_layers_before_predictor,
freeze_batchnorm=freeze_batchnorm,
inplace_batchnorm_update=inplace_batchnorm_update,
kernel_size=kernel_size,
apply_batch_norm=apply_batch_norm,
share_prediction_tower=share_prediction_tower,
use_depthwise=use_depthwise,
name=name))