def test_forward(self, use_separable_conv, use_sync_bn):
retinanet_head = dense_prediction_heads.RetinaNetHead(
min_level=3,
max_level=4,
num_classes=3,
num_anchors_per_location=3,
num_convs=2,
num_filters=256,
use_separable_conv=use_separable_conv,
activation='relu',
use_sync_bn=use_sync_bn,
norm_momentum=0.99,
norm_epsilon=0.001,
kernel_regularizer=None,
bias_regularizer=None,
)
features = {
3: np.random.rand(2, 128, 128, 16),
4: np.random.rand(2, 64, 64, 16),
}
scores, boxes = retinanet_head(features)
self.assertAllEqual(scores[3].numpy().shape, [2, 128, 128, 9])
self.assertAllEqual(scores[4].numpy().shape, [2, 64, 64, 9])
self.assertAllEqual(boxes[3].numpy().shape, [2, 128, 128, 12])
self.assertAllEqual(boxes[4].numpy().shape, [2, 64, 64, 12])
def test_serialize_deserialize(self):
"""Validate the network can be serialized and deserialized."""
num_classes = 3
min_level = 3
max_level = 7
num_scales = 3
aspect_ratios = [1.0]
num_anchors_per_location = num_scales * len(aspect_ratios)
backbone = resnet.ResNet(model_id=50)
decoder = fpn.FPN(input_specs=backbone.output_specs,
min_level=min_level,
max_level=max_level)
head = dense_prediction_heads.RetinaNetHead(
min_level=min_level,
max_level=max_level,
num_classes=num_classes,
num_anchors_per_location=num_anchors_per_location)
generator = detection_generator.MultilevelDetectionGenerator(
max_num_detections=10)
model = retinanet_model.RetinaNetModel(backbone=backbone,
decoder=decoder,
head=head,
detection_generator=generator)
config = model.get_config()
new_model = retinanet_model.RetinaNetModel.from_config(config)
# Validate that the config can be forced to JSON.
_ = new_model.to_json()
# If the serialization was successful, the new config should match the old.
self.assertAllEqual(model.get_config(), new_model.get_config())
def test_forward(self, use_separable_conv, use_sync_bn, has_att_heads):
if has_att_heads:
attribute_heads = [dict(name='depth', type='regression', size=1)]
else:
attribute_heads = None
retinanet_head = dense_prediction_heads.RetinaNetHead(
min_level=3,
max_level=4,
num_classes=3,
num_anchors_per_location=3,
num_convs=2,
num_filters=256,
attribute_heads=attribute_heads,
use_separable_conv=use_separable_conv,
activation='relu',
use_sync_bn=use_sync_bn,
norm_momentum=0.99,
norm_epsilon=0.001,
kernel_regularizer=None,
bias_regularizer=None,
)
features = {
'3': np.random.rand(2, 128, 128, 16),
'4': np.random.rand(2, 64, 64, 16),
}
scores, boxes, attributes = retinanet_head(features)
self.assertAllEqual(scores['3'].numpy().shape, [2, 128, 128, 9])
self.assertAllEqual(scores['4'].numpy().shape, [2, 64, 64, 9])
self.assertAllEqual(boxes['3'].numpy().shape, [2, 128, 128, 12])
self.assertAllEqual(boxes['4'].numpy().shape, [2, 64, 64, 12])
if has_att_heads:
for att in attributes.values():
self.assertAllEqual(att['3'].numpy().shape, [2, 128, 128, 3])
self.assertAllEqual(att['4'].numpy().shape, [2, 64, 64, 3])
def build_retinanet(
input_specs: tf.keras.layers.InputSpec,
model_config: retinanet_cfg.RetinaNet,
l2_regularizer: tf.keras.regularizers.Regularizer = None
) -> tf.keras.Model:
"""Builds RetinaNet model."""
norm_activation_config = model_config.norm_activation
backbone = backbones.factory.build_backbone(
input_specs=input_specs,
backbone_config=model_config.backbone,
norm_activation_config=norm_activation_config,
l2_regularizer=l2_regularizer)
backbone(tf.keras.Input(input_specs.shape[1:]))
decoder = decoders.factory.build_decoder(input_specs=backbone.output_specs,
model_config=model_config,
l2_regularizer=l2_regularizer)
head_config = model_config.head
generator_config = model_config.detection_generator
num_anchors_per_location = (len(model_config.anchor.aspect_ratios) *
model_config.anchor.num_scales)
head = dense_prediction_heads.RetinaNetHead(
min_level=model_config.min_level,
max_level=model_config.max_level,
num_classes=model_config.num_classes,
num_anchors_per_location=num_anchors_per_location,
num_convs=head_config.num_convs,
num_filters=head_config.num_filters,
attribute_heads=[
cfg.as_dict() for cfg in (head_config.attribute_heads or [])
],
use_separable_conv=head_config.use_separable_conv,
activation=norm_activation_config.activation,
use_sync_bn=norm_activation_config.use_sync_bn,
norm_momentum=norm_activation_config.norm_momentum,
norm_epsilon=norm_activation_config.norm_epsilon,
kernel_regularizer=l2_regularizer)
detection_generator_obj = detection_generator.MultilevelDetectionGenerator(
apply_nms=generator_config.apply_nms,
pre_nms_top_k=generator_config.pre_nms_top_k,
pre_nms_score_threshold=generator_config.pre_nms_score_threshold,
nms_iou_threshold=generator_config.nms_iou_threshold,
max_num_detections=generator_config.max_num_detections,
use_batched_nms=generator_config.use_batched_nms,
use_cpu_nms=generator_config.use_cpu_nms)
model = retinanet_model.RetinaNetModel(
backbone,
decoder,
head,
detection_generator_obj,
min_level=model_config.min_level,
max_level=model_config.max_level,
num_scales=model_config.anchor.num_scales,
aspect_ratios=model_config.anchor.aspect_ratios,
anchor_size=model_config.anchor.anchor_size)
return model
def test_num_params(self,
num_classes,
min_level,
max_level,
num_scales,
aspect_ratios,
resnet_model_id,
use_separable_conv,
fpn_num_filters,
head_num_convs,
head_num_filters,
expected_num_params):
num_anchors_per_location = num_scales * len(aspect_ratios)
image_size = 384
images = np.random.rand(2, image_size, image_size, 3)
image_shape = np.array([[image_size, image_size], [image_size, image_size]])
anchor_boxes = anchor.Anchor(
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=3,
image_size=(image_size, image_size)).multilevel_boxes
for l in anchor_boxes:
anchor_boxes[l] = tf.tile(
tf.expand_dims(anchor_boxes[l], axis=0), [2, 1, 1, 1])
backbone = resnet.ResNet(model_id=resnet_model_id)
decoder = fpn.FPN(
input_specs=backbone.output_specs,
min_level=min_level,
max_level=max_level,
num_filters=fpn_num_filters,
use_separable_conv=use_separable_conv)
head = dense_prediction_heads.RetinaNetHead(
min_level=min_level,
max_level=max_level,
num_classes=num_classes,
num_anchors_per_location=num_anchors_per_location,
use_separable_conv=use_separable_conv,
num_convs=head_num_convs,
num_filters=head_num_filters)
generator = detection_generator.MultilevelDetectionGenerator(
max_num_detections=10)
model = retinanet_model.RetinaNetModel(
backbone=backbone,
decoder=decoder,
head=head,
detection_generator=generator)
_ = model(images, image_shape, anchor_boxes, training=True)
self.assertEqual(expected_num_params, model.count_params())
def test_serialize_deserialize(self):
retinanet_head = dense_prediction_heads.RetinaNetHead(
min_level=3,
max_level=7,
num_classes=3,
num_anchors_per_location=9,
num_convs=2,
num_filters=16,
use_separable_conv=False,
activation='relu',
use_sync_bn=False,
norm_momentum=0.99,
norm_epsilon=0.001,
kernel_regularizer=None,
bias_regularizer=None,
)
config = retinanet_head.get_config()
new_retinanet_head = (
dense_prediction_heads.RetinaNetHead.from_config(config))
self.assertAllEqual(retinanet_head.get_config(),
new_retinanet_head.get_config())
def test_forward(self, strategy, image_size, training, has_att_heads):
"""Test for creation of a R50-FPN RetinaNet."""
tf.keras.backend.set_image_data_format('channels_last')
num_classes = 3
min_level = 3
max_level = 7
num_scales = 3
aspect_ratios = [1.0]
num_anchors_per_location = num_scales * len(aspect_ratios)
images = np.random.rand(2, image_size[0], image_size[1], 3)
image_shape = np.array([[image_size[0], image_size[1]],
[image_size[0], image_size[1]]])
with strategy.scope():
anchor_gen = anchor.build_anchor_generator(
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=3)
anchor_boxes = anchor_gen(image_size)
for l in anchor_boxes:
anchor_boxes[l] = tf.tile(
tf.expand_dims(anchor_boxes[l], axis=0), [2, 1, 1, 1])
backbone = resnet.ResNet(model_id=50)
decoder = fpn.FPN(input_specs=backbone.output_specs,
min_level=min_level,
max_level=max_level)
if has_att_heads:
attribute_heads = {'depth': ('regression', 1)}
else:
attribute_heads = None
head = dense_prediction_heads.RetinaNetHead(
min_level=min_level,
max_level=max_level,
num_classes=num_classes,
attribute_heads=attribute_heads,
num_anchors_per_location=num_anchors_per_location)
generator = detection_generator.MultilevelDetectionGenerator(
max_num_detections=10)
model = retinanet_model.RetinaNetModel(
backbone=backbone,
decoder=decoder,
head=head,
detection_generator=generator)
model_outputs = model(images,
image_shape,
anchor_boxes,
training=training)
if training:
cls_outputs = model_outputs['cls_outputs']
box_outputs = model_outputs['box_outputs']
att_outputs = model_outputs['att_outputs']
for level in range(min_level, max_level + 1):
self.assertIn(str(level), cls_outputs)
self.assertIn(str(level), box_outputs)
self.assertAllEqual([
2, image_size[0] // 2**level, image_size[1] // 2**level,
num_classes * num_anchors_per_location
], cls_outputs[str(level)].numpy().shape)
self.assertAllEqual([
2, image_size[0] // 2**level, image_size[1] // 2**level,
4 * num_anchors_per_location
], box_outputs[str(level)].numpy().shape)
if has_att_heads:
for att in att_outputs.values():
self.assertAllEqual([
2, image_size[0] // 2**level, image_size[1] //
2**level, 1 * num_anchors_per_location
], att[str(level)].numpy().shape)
else:
self.assertIn('detection_boxes', model_outputs)
self.assertIn('detection_scores', model_outputs)
self.assertIn('detection_classes', model_outputs)
self.assertIn('detection_attributes', model_outputs)
self.assertIn('num_detections', model_outputs)
self.assertAllEqual([2, 10, 4],
model_outputs['detection_boxes'].numpy().shape)
self.assertAllEqual(
[2, 10], model_outputs['detection_scores'].numpy().shape)
self.assertAllEqual(
[2, 10], model_outputs['detection_classes'].numpy().shape)
self.assertAllEqual([
2,
], model_outputs['num_detections'].numpy().shape)
if has_att_heads:
self.assertAllEqual([2, 10, 1],
model_outputs['detection_attributes']
['depth'].numpy().shape)
def test_build_model(self, use_separable_conv, build_anchor_boxes,
is_training, has_att_heads):
num_classes = 3
min_level = 3
max_level = 7
num_scales = 3
aspect_ratios = [1.0]
anchor_size = 3
fpn_num_filters = 256
head_num_convs = 4
head_num_filters = 256
num_anchors_per_location = num_scales * len(aspect_ratios)
image_size = 384
images = np.random.rand(2, image_size, image_size, 3)
image_shape = np.array([[image_size, image_size],
[image_size, image_size]])
if build_anchor_boxes:
anchor_boxes = anchor.Anchor(
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=anchor_size,
image_size=(image_size, image_size)).multilevel_boxes
for l in anchor_boxes:
anchor_boxes[l] = tf.tile(
tf.expand_dims(anchor_boxes[l], axis=0), [2, 1, 1, 1])
else:
anchor_boxes = None
if has_att_heads:
attribute_heads = [dict(name='depth', type='regression', size=1)]
else:
attribute_heads = None
backbone = resnet.ResNet(model_id=50)
decoder = fpn.FPN(input_specs=backbone.output_specs,
min_level=min_level,
max_level=max_level,
num_filters=fpn_num_filters,
use_separable_conv=use_separable_conv)
head = dense_prediction_heads.RetinaNetHead(
min_level=min_level,
max_level=max_level,
num_classes=num_classes,
attribute_heads=attribute_heads,
num_anchors_per_location=num_anchors_per_location,
use_separable_conv=use_separable_conv,
num_convs=head_num_convs,
num_filters=head_num_filters)
generator = detection_generator.MultilevelDetectionGenerator(
max_num_detections=10)
model = retinanet_model.RetinaNetModel(backbone=backbone,
decoder=decoder,
head=head,
detection_generator=generator,
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=anchor_size)
_ = model(images, image_shape, anchor_boxes, training=is_training)