def test_get_predictions_with_feature_maps_of_dynamic_shape(
self):
image_features = tf.placeholder(dtype=tf.float32, shape=[4, None, None, 64])
conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor(
is_training=False,
num_classes=0,
conv_hyperparams=self._build_arg_scope_with_conv_hyperparams(),
depth=32,
num_layers_before_predictor=1,
box_code_size=4)
box_predictions = conv_box_predictor.predict(
[image_features], num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = tf.concat(box_predictions[box_predictor.BOX_ENCODINGS],
axis=1)
objectness_predictions = tf.concat(box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND], axis=1)
init_op = tf.global_variables_initializer()
resolution = 32
expected_num_anchors = resolution*resolution*5
with self.test_session() as sess:
sess.run(init_op)
(box_encodings_shape,
objectness_predictions_shape) = sess.run(
[tf.shape(box_encodings), tf.shape(objectness_predictions)],
feed_dict={image_features:
np.random.rand(4, resolution, resolution, 64)})
self.assertAllEqual(box_encodings_shape, [4, expected_num_anchors, 1, 4])
self.assertAllEqual(objectness_predictions_shape,
[4, expected_num_anchors, 1])
def graph_fn(image_features):
conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor(
is_training=False,
num_classes=0,
conv_hyperparams=self._build_arg_scope_with_conv_hyperparams(),
depth=32,
num_layers_before_predictor=1,
box_code_size=4)
box_predictions = conv_box_predictor.predict(
[image_features], num_predictions_per_location=[5],
scope='BoxPredictor')
box_encodings = box_predictions[box_predictor.BOX_ENCODINGS]
objectness_predictions = box_predictions[
box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND]
return (box_encodings, objectness_predictions)
def graph_fn(image_features1, image_features2):
conv_box_predictor = box_predictor.WeightSharedConvolutionalBoxPredictor(
is_training=False,
num_classes=num_classes_without_background,
conv_hyperparams=self._build_arg_scope_with_conv_hyperparams(),
depth=32,
num_layers_before_predictor=2,
box_code_size=4)
box_predictions = conv_box_predictor.predict(
[image_features1, image_features2],
num_predictions_per_location=[5, 5],
scope='BoxPredictor')
box_encodings = tf.concat(
box_predictions[box_predictor.BOX_ENCODINGS], axis=1)
class_predictions_with_background = tf.concat(
box_predictions[box_predictor.CLASS_PREDICTIONS_WITH_BACKGROUND],
axis=1)
return (box_encodings, class_predictions_with_background)
def build(argscope_fn, box_predictor_config, is_training, num_classes):
"""Builds box predictor based on the configuration.
Builds box predictor based on the configuration. See box_predictor.proto for
configurable options. Also, see box_predictor.py for more details.
Args:
argscope_fn: A function that takes the following inputs:
* hyperparams_pb2.Hyperparams proto
* a boolean indicating if the model is in training mode.
and returns a tf slim argscope for Conv and FC hyperparameters.
box_predictor_config: box_predictor_pb2.BoxPredictor proto containing
configuration.
is_training: Whether the models is in training mode.
num_classes: Number of classes to predict.
Returns:
box_predictor: box_predictor.BoxPredictor object.
Raises:
ValueError: On unknown box predictor.
"""
if not isinstance(box_predictor_config, box_predictor_pb2.BoxPredictor):
raise ValueError('box_predictor_config not of type '
'box_predictor_pb2.BoxPredictor.')
box_predictor_oneof = box_predictor_config.WhichOneof(
'box_predictor_oneof')
if box_predictor_oneof == 'convolutional_box_predictor':
conv_box_predictor = box_predictor_config.convolutional_box_predictor
conv_hyperparams = argscope_fn(conv_box_predictor.conv_hyperparams,
is_training)
box_predictor_object = box_predictor.ConvolutionalBoxPredictor(
is_training=is_training,
num_classes=num_classes,
conv_hyperparams=conv_hyperparams,
min_depth=conv_box_predictor.min_depth,
max_depth=conv_box_predictor.max_depth,
num_layers_before_predictor=(
conv_box_predictor.num_layers_before_predictor),
use_dropout=conv_box_predictor.use_dropout,
dropout_keep_prob=conv_box_predictor.dropout_keep_probability,
kernel_size=conv_box_predictor.kernel_size,
box_code_size=conv_box_predictor.box_code_size,
apply_sigmoid_to_scores=conv_box_predictor.apply_sigmoid_to_scores,
class_prediction_bias_init=(
conv_box_predictor.class_prediction_bias_init),
use_depthwise=conv_box_predictor.use_depthwise)
return box_predictor_object
if box_predictor_oneof == 'weight_shared_convolutional_box_predictor':
conv_box_predictor = (
box_predictor_config.weight_shared_convolutional_box_predictor)
conv_hyperparams = argscope_fn(conv_box_predictor.conv_hyperparams,
is_training)
box_predictor_object = box_predictor.WeightSharedConvolutionalBoxPredictor(
is_training=is_training,
num_classes=num_classes,
conv_hyperparams=conv_hyperparams,
depth=conv_box_predictor.depth,
num_layers_before_predictor=(
conv_box_predictor.num_layers_before_predictor),
kernel_size=conv_box_predictor.kernel_size,
box_code_size=conv_box_predictor.box_code_size,
class_prediction_bias_init=conv_box_predictor.
class_prediction_bias_init)
return box_predictor_object
if box_predictor_oneof == 'mask_rcnn_box_predictor':
mask_rcnn_box_predictor = box_predictor_config.mask_rcnn_box_predictor
fc_hyperparams = argscope_fn(mask_rcnn_box_predictor.fc_hyperparams,
is_training)
conv_hyperparams = None
if mask_rcnn_box_predictor.HasField('conv_hyperparams'):
conv_hyperparams = argscope_fn(
mask_rcnn_box_predictor.conv_hyperparams, is_training)
box_predictor_object = box_predictor.MaskRCNNBoxPredictor(
is_training=is_training,
num_classes=num_classes,
fc_hyperparams=fc_hyperparams,
use_dropout=mask_rcnn_box_predictor.use_dropout,
dropout_keep_prob=mask_rcnn_box_predictor.dropout_keep_probability,
box_code_size=mask_rcnn_box_predictor.box_code_size,
conv_hyperparams=conv_hyperparams,
predict_instance_masks=mask_rcnn_box_predictor.
predict_instance_masks,
mask_height=mask_rcnn_box_predictor.mask_height,
mask_width=mask_rcnn_box_predictor.mask_width,
mask_prediction_num_conv_layers=(
mask_rcnn_box_predictor.mask_prediction_num_conv_layers),
mask_prediction_conv_depth=(
mask_rcnn_box_predictor.mask_prediction_conv_depth),
predict_keypoints=mask_rcnn_box_predictor.predict_keypoints)
return box_predictor_object
if box_predictor_oneof == 'rfcn_box_predictor':
rfcn_box_predictor = box_predictor_config.rfcn_box_predictor
conv_hyperparams = argscope_fn(rfcn_box_predictor.conv_hyperparams,
is_training)
box_predictor_object = box_predictor.RfcnBoxPredictor(
is_training=is_training,
num_classes=num_classes,
conv_hyperparams=conv_hyperparams,
crop_size=[
rfcn_box_predictor.crop_height, rfcn_box_predictor.crop_width
],
num_spatial_bins=[
rfcn_box_predictor.num_spatial_bins_height,
rfcn_box_predictor.num_spatial_bins_width
],
depth=rfcn_box_predictor.depth,
box_code_size=rfcn_box_predictor.box_code_size)
return box_predictor_object
raise ValueError('Unknown box predictor: {}'.format(box_predictor_oneof))