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_serialize_deserialize(self):
# Create a network object that sets all of its config options.
kwargs = dict(
input_specs=resnet.ResNet(model_id=50).output_specs,
min_level=3,
max_level=7,
num_filters=256,
use_separable_conv=False,
use_sync_bn=False,
activation='relu',
norm_momentum=0.99,
norm_epsilon=0.001,
kernel_initializer='VarianceScaling',
kernel_regularizer=None,
bias_regularizer=None,
)
network = fpn.FPN(**kwargs)
expected_config = dict(kwargs)
self.assertEqual(network.get_config(), expected_config)
# Create another network object from the first object's config.
new_network = fpn.FPN.from_config(network.get_config())
# Validate that the config can be forced to JSON.
_ = new_network.to_json()
# If the serialization was successful, the new config should match the old.
self.assertAllEqual(network.get_config(), new_network.get_config())
def test_checkpoint(self, include_mask):
input_specs = tf.keras.layers.InputSpec(shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=3,
max_level=7,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(min_level=3,
max_level=7,
num_anchors_per_location=3)
detection_head = instance_heads.DetectionHead(num_classes=2)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
if include_mask:
mask_head = instance_heads.MaskHead(num_classes=2,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(
crop_size=14)
else:
mask_head = None
mask_sampler_obj = None
mask_roi_aligner_obj = None
model = maskrcnn_model.MaskRCNNModel(backbone, decoder, rpn_head,
detection_head, roi_generator_obj,
roi_sampler_obj, roi_aligner_obj,
detection_generator_obj,
mask_head, mask_sampler_obj,
mask_roi_aligner_obj)
expect_checkpoint_items = dict(backbone=backbone,
decoder=decoder,
rpn_head=rpn_head,
detection_head=detection_head)
if include_mask:
expect_checkpoint_items['mask_head'] = mask_head
self.assertAllEqual(expect_checkpoint_items, model.checkpoint_items)
# Test save and load checkpoints.
ckpt = tf.train.Checkpoint(model=model, **model.checkpoint_items)
save_dir = self.create_tempdir().full_path
ckpt.save(os.path.join(save_dir, 'ckpt'))
partial_ckpt = tf.train.Checkpoint(backbone=backbone)
partial_ckpt.restore(tf.train.latest_checkpoint(
save_dir)).expect_partial().assert_existing_objects_matched()
if include_mask:
partial_ckpt_mask = tf.train.Checkpoint(backbone=backbone,
mask_head=mask_head)
partial_ckpt_mask.restore(tf.train.latest_checkpoint(
save_dir)).expect_partial().assert_existing_objects_matched()
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, include_mask):
input_specs = tf.keras.layers.InputSpec(shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=3,
max_level=7,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(min_level=3,
max_level=7,
num_anchors_per_location=3)
detection_head = instance_heads.DetectionHead(num_classes=2)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
if include_mask:
mask_head = instance_heads.MaskHead(num_classes=2,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(
crop_size=14)
else:
mask_head = None
mask_sampler_obj = None
mask_roi_aligner_obj = None
model = maskrcnn_model.MaskRCNNModel(backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
min_level=3,
max_level=7,
num_scales=3,
aspect_ratios=[1.0],
anchor_size=3)
config = model.get_config()
new_model = maskrcnn_model.MaskRCNNModel.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 construct_model_and_anchors(image_size, use_gt_boxes_for_masks):
num_classes = 3
min_level = 3
max_level = 4
num_scales = 3
aspect_ratios = [1.0]
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).multilevel_boxes
num_anchors_per_location = len(aspect_ratios) * num_scales
input_specs = tf.keras.layers.InputSpec(shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=min_level,
max_level=max_level,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(
min_level=min_level,
max_level=max_level,
num_anchors_per_location=num_anchors_per_location)
detection_head = instance_heads.DetectionHead(num_classes=num_classes)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
mask_head = deep_instance_heads.DeepMaskHead(num_classes=num_classes,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(crop_size=14)
model = maskrcnn_model.DeepMaskRCNNModel(
backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
use_gt_boxes_for_masks=use_gt_boxes_for_masks)
return model, anchor_boxes
def test_serialize_deserialize(self):
"""Validate the network can be serialized and deserialized."""
num_classes = 3
backbone = backbones.ResNet(model_id=50)
decoder = fpn.FPN(input_specs=backbone.output_specs,
min_level=3,
max_level=7)
head = segmentation_heads.SegmentationHead(num_classes, level=3)
model = segmentation_model.SegmentationModel(backbone=backbone,
decoder=decoder,
head=head)
config = model.get_config()
new_model = segmentation_model.SegmentationModel.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_segmentation_network_creation(self, input_size, level):
"""Test for creation of a segmentation network."""
num_classes = 10
inputs = np.random.rand(2, input_size, input_size, 3)
tf.keras.backend.set_image_data_format('channels_last')
backbone = backbones.ResNet(model_id=50)
decoder = fpn.FPN(input_specs=backbone.output_specs,
min_level=2,
max_level=7)
head = segmentation_heads.SegmentationHead(num_classes, level=level)
model = segmentation_model.SegmentationModel(backbone=backbone,
decoder=decoder,
head=head)
logits = model(inputs)
self.assertAllEqual([
2, input_size // (2**level), input_size // (2**level), num_classes
],
logits.numpy().shape)
def test_network_creation(self, input_size, min_level, max_level,
use_separable_conv):
"""Test creation of FPN."""
tf.keras.backend.set_image_data_format('channels_last')
inputs = tf.keras.Input(shape=(input_size, input_size, 3),
batch_size=1)
backbone = resnet.ResNet(model_id=50)
network = fpn.FPN(input_specs=backbone.output_specs,
min_level=min_level,
max_level=max_level,
use_separable_conv=use_separable_conv)
endpoints = backbone(inputs)
feats = network(endpoints)
for level in range(min_level, max_level + 1):
self.assertIn(str(level), feats)
self.assertAllEqual(
[1, input_size // 2**level, input_size // 2**level, 256],
feats[str(level)].shape.as_list())
def test_forward(self, strategy, include_mask, build_anchor_boxes,
training, use_cascade_heads):
num_classes = 3
min_level = 3
max_level = 4
num_scales = 3
aspect_ratios = [1.0]
anchor_size = 3
if use_cascade_heads:
cascade_iou_thresholds = [0.6]
class_agnostic_bbox_pred = True
cascade_class_ensemble = True
else:
cascade_iou_thresholds = None
class_agnostic_bbox_pred = False
cascade_class_ensemble = False
image_size = (256, 256)
images = np.random.rand(2, image_size[0], image_size[1], 3)
image_shape = np.array([[224, 100], [100, 224]])
with strategy.scope():
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).multilevel_boxes
else:
anchor_boxes = None
num_anchors_per_location = len(aspect_ratios) * num_scales
input_specs = tf.keras.layers.InputSpec(
shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=min_level,
max_level=max_level,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(
min_level=min_level,
max_level=max_level,
num_anchors_per_location=num_anchors_per_location)
detection_head = instance_heads.DetectionHead(
num_classes=num_classes,
class_agnostic_bbox_pred=class_agnostic_bbox_pred)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_cascade = []
roi_sampler_obj = roi_sampler.ROISampler()
roi_sampler_cascade.append(roi_sampler_obj)
if cascade_iou_thresholds:
for iou in cascade_iou_thresholds:
roi_sampler_obj = roi_sampler.ROISampler(
mix_gt_boxes=False,
foreground_iou_threshold=iou,
background_iou_high_threshold=iou,
background_iou_low_threshold=0.0,
skip_subsampling=True)
roi_sampler_cascade.append(roi_sampler_obj)
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
if include_mask:
mask_head = instance_heads.MaskHead(num_classes=num_classes,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(
mask_target_size=28, num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(
crop_size=14)
else:
mask_head = None
mask_sampler_obj = None
mask_roi_aligner_obj = None
model = maskrcnn_model.MaskRCNNModel(
backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
class_agnostic_bbox_pred=class_agnostic_bbox_pred,
cascade_class_ensemble=cascade_class_ensemble,
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=anchor_size)
gt_boxes = np.array(
[[[10, 10, 15, 15], [2.5, 2.5, 7.5, 7.5], [-1, -1, -1, -1]],
[[100, 100, 150, 150], [-1, -1, -1, -1], [-1, -1, -1, -1]]],
dtype=np.float32)
gt_classes = np.array([[2, 1, -1], [1, -1, -1]], dtype=np.int32)
if include_mask:
gt_masks = np.ones((2, 3, 100, 100))
else:
gt_masks = None
results = model(images,
image_shape,
anchor_boxes,
gt_boxes,
gt_classes,
gt_masks,
training=training)
self.assertIn('rpn_boxes', results)
self.assertIn('rpn_scores', results)
if training:
self.assertIn('class_targets', results)
self.assertIn('box_targets', results)
self.assertIn('class_outputs', results)
self.assertIn('box_outputs', results)
if include_mask:
self.assertIn('mask_outputs', results)
else:
self.assertIn('detection_boxes', results)
self.assertIn('detection_scores', results)
self.assertIn('detection_classes', results)
self.assertIn('num_detections', results)
if include_mask:
self.assertIn('detection_masks', results)
def test_forward(self, strategy, training, shared_backbone, shared_decoder,
generate_panoptic_masks):
num_classes = 3
min_level = 2
max_level = 6
num_scales = 3
aspect_ratios = [1.0]
anchor_size = 3
segmentation_resnet_model_id = 101
aspp_dilation_rates = [6, 12, 18]
aspp_decoder_level = 2
fpn_decoder_level = 2
class_agnostic_bbox_pred = False
cascade_class_ensemble = False
image_size = (256, 256)
images = tf.random.normal([2, image_size[0], image_size[1], 3])
image_info = tf.convert_to_tensor([[[224, 100], [224, 100], [1, 1],
[0, 0]],
[[224, 100], [224, 100], [1, 1],
[0, 0]]])
shared_decoder = shared_decoder and shared_backbone
with strategy.scope():
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).multilevel_boxes
num_anchors_per_location = len(aspect_ratios) * num_scales
input_specs = tf.keras.layers.InputSpec(
shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=min_level,
max_level=max_level,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(
min_level=min_level,
max_level=max_level,
num_anchors_per_location=num_anchors_per_location)
detection_head = instance_heads.DetectionHead(
num_classes=num_classes,
class_agnostic_bbox_pred=class_agnostic_bbox_pred)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_cascade = []
roi_sampler_obj = roi_sampler.ROISampler()
roi_sampler_cascade.append(roi_sampler_obj)
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
if generate_panoptic_masks:
panoptic_segmentation_generator_obj = panoptic_segmentation_generator.PanopticSegmentationGenerator(
output_size=list(image_size),
max_num_detections=100,
stuff_classes_offset=90)
else:
panoptic_segmentation_generator_obj = None
mask_head = instance_heads.MaskHead(num_classes=num_classes,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(
crop_size=14)
if shared_backbone:
segmentation_backbone = None
else:
segmentation_backbone = resnet.ResNet(
model_id=segmentation_resnet_model_id)
if not shared_decoder:
feature_fusion = 'deeplabv3plus'
level = aspp_decoder_level
segmentation_decoder = aspp.ASPP(
level=level, dilation_rates=aspp_dilation_rates)
else:
feature_fusion = 'panoptic_fpn_fusion'
level = fpn_decoder_level
segmentation_decoder = None
segmentation_head = segmentation_heads.SegmentationHead(
num_classes=2, # stuff and common class for things,
level=level,
feature_fusion=feature_fusion,
decoder_min_level=min_level,
decoder_max_level=max_level,
num_convs=2)
model = panoptic_maskrcnn_model.PanopticMaskRCNNModel(
backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
panoptic_segmentation_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
segmentation_backbone=segmentation_backbone,
segmentation_decoder=segmentation_decoder,
segmentation_head=segmentation_head,
class_agnostic_bbox_pred=class_agnostic_bbox_pred,
cascade_class_ensemble=cascade_class_ensemble,
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=anchor_size)
gt_boxes = tf.convert_to_tensor(
[[[10, 10, 15, 15], [2.5, 2.5, 7.5, 7.5], [-1, -1, -1, -1]],
[[100, 100, 150, 150], [-1, -1, -1, -1], [-1, -1, -1, -1]]],
dtype=tf.float32)
gt_classes = tf.convert_to_tensor([[2, 1, -1], [1, -1, -1]],
dtype=tf.int32)
gt_masks = tf.ones((2, 3, 100, 100))
results = model(images,
image_info,
anchor_boxes,
gt_boxes,
gt_classes,
gt_masks,
training=training)
self.assertIn('rpn_boxes', results)
self.assertIn('rpn_scores', results)
if training:
self.assertIn('class_targets', results)
self.assertIn('box_targets', results)
self.assertIn('class_outputs', results)
self.assertIn('box_outputs', results)
self.assertIn('mask_outputs', results)
else:
self.assertIn('detection_boxes', results)
self.assertIn('detection_scores', results)
self.assertIn('detection_classes', results)
self.assertIn('num_detections', results)
self.assertIn('detection_masks', results)
self.assertIn('segmentation_outputs', results)
self.assertAllEqual([
2, image_size[0] // (2**level), image_size[1] // (2**level), 2
], results['segmentation_outputs'].numpy().shape)
if generate_panoptic_masks:
self.assertIn('panoptic_outputs', results)
self.assertIn('category_mask', results['panoptic_outputs'])
self.assertIn('instance_mask', results['panoptic_outputs'])
self.assertAllEqual(
[2, image_size[0], image_size[1]],
results['panoptic_outputs']['category_mask'].numpy().shape)
self.assertAllEqual(
[2, image_size[0], image_size[1]],
results['panoptic_outputs']['instance_mask'].numpy().shape)
else:
self.assertNotIn('panoptic_outputs', results)
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_serialize_deserialize(self, shared_backbone, shared_decoder):
input_specs = tf.keras.layers.InputSpec(shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=3,
max_level=7,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(min_level=3,
max_level=7,
num_anchors_per_location=3)
detection_head = instance_heads.DetectionHead(num_classes=2)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
panoptic_segmentation_generator_obj = panoptic_segmentation_generator.PanopticSegmentationGenerator(
output_size=[None, None],
max_num_detections=100,
stuff_classes_offset=90)
segmentation_resnet_model_id = 101
aspp_dilation_rates = [6, 12, 18]
min_level = 2
max_level = 6
aspp_decoder_level = 2
fpn_decoder_level = 2
shared_decoder = shared_decoder and shared_backbone
mask_head = instance_heads.MaskHead(num_classes=2, upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(crop_size=14)
if shared_backbone:
segmentation_backbone = None
else:
segmentation_backbone = resnet.ResNet(
model_id=segmentation_resnet_model_id)
if not shared_decoder:
feature_fusion = 'deeplabv3plus'
level = aspp_decoder_level
segmentation_decoder = aspp.ASPP(
level=level, dilation_rates=aspp_dilation_rates)
else:
feature_fusion = 'panoptic_fpn_fusion'
level = fpn_decoder_level
segmentation_decoder = None
segmentation_head = segmentation_heads.SegmentationHead(
num_classes=2, # stuff and common class for things,
level=level,
feature_fusion=feature_fusion,
decoder_min_level=min_level,
decoder_max_level=max_level,
num_convs=2)
model = panoptic_maskrcnn_model.PanopticMaskRCNNModel(
backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
panoptic_segmentation_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
segmentation_backbone=segmentation_backbone,
segmentation_decoder=segmentation_decoder,
segmentation_head=segmentation_head,
min_level=min_level,
max_level=max_level,
num_scales=3,
aspect_ratios=[1.0],
anchor_size=3)
config = model.get_config()
new_model = panoptic_maskrcnn_model.PanopticMaskRCNNModel.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_checkpoint(self, shared_backbone, shared_decoder):
input_specs = tf.keras.layers.InputSpec(shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=3,
max_level=7,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(min_level=3,
max_level=7,
num_anchors_per_location=3)
detection_head = instance_heads.DetectionHead(num_classes=2)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
panoptic_segmentation_generator_obj = panoptic_segmentation_generator.PanopticSegmentationGenerator(
output_size=[None, None],
max_num_detections=100,
stuff_classes_offset=90)
segmentation_resnet_model_id = 101
aspp_dilation_rates = [6, 12, 18]
min_level = 2
max_level = 6
aspp_decoder_level = 2
fpn_decoder_level = 2
shared_decoder = shared_decoder and shared_backbone
mask_head = instance_heads.MaskHead(num_classes=2, upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(crop_size=14)
if shared_backbone:
segmentation_backbone = None
else:
segmentation_backbone = resnet.ResNet(
model_id=segmentation_resnet_model_id)
if not shared_decoder:
feature_fusion = 'deeplabv3plus'
level = aspp_decoder_level
segmentation_decoder = aspp.ASPP(
level=level, dilation_rates=aspp_dilation_rates)
else:
feature_fusion = 'panoptic_fpn_fusion'
level = fpn_decoder_level
segmentation_decoder = None
segmentation_head = segmentation_heads.SegmentationHead(
num_classes=2, # stuff and common class for things,
level=level,
feature_fusion=feature_fusion,
decoder_min_level=min_level,
decoder_max_level=max_level,
num_convs=2)
model = panoptic_maskrcnn_model.PanopticMaskRCNNModel(
backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
panoptic_segmentation_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
segmentation_backbone=segmentation_backbone,
segmentation_decoder=segmentation_decoder,
segmentation_head=segmentation_head,
min_level=max_level,
max_level=max_level,
num_scales=3,
aspect_ratios=[1.0],
anchor_size=3)
expect_checkpoint_items = dict(backbone=backbone,
decoder=decoder,
rpn_head=rpn_head,
detection_head=[detection_head])
expect_checkpoint_items['mask_head'] = mask_head
if not shared_backbone:
expect_checkpoint_items[
'segmentation_backbone'] = segmentation_backbone
if not shared_decoder:
expect_checkpoint_items[
'segmentation_decoder'] = segmentation_decoder
expect_checkpoint_items['segmentation_head'] = segmentation_head
self.assertAllEqual(expect_checkpoint_items, model.checkpoint_items)
# Test save and load checkpoints.
ckpt = tf.train.Checkpoint(model=model, **model.checkpoint_items)
save_dir = self.create_tempdir().full_path
ckpt.save(os.path.join(save_dir, 'ckpt'))
partial_ckpt = tf.train.Checkpoint(backbone=backbone)
partial_ckpt.read(tf.train.latest_checkpoint(
save_dir)).expect_partial().assert_existing_objects_matched()
partial_ckpt_mask = tf.train.Checkpoint(backbone=backbone,
mask_head=mask_head)
partial_ckpt_mask.restore(tf.train.latest_checkpoint(
save_dir)).expect_partial().assert_existing_objects_matched()
if not shared_backbone:
partial_ckpt_segmentation = tf.train.Checkpoint(
segmentation_backbone=segmentation_backbone,
segmentation_decoder=segmentation_decoder,
segmentation_head=segmentation_head)
elif not shared_decoder:
partial_ckpt_segmentation = tf.train.Checkpoint(
segmentation_decoder=segmentation_decoder,
segmentation_head=segmentation_head)
else:
partial_ckpt_segmentation = tf.train.Checkpoint(
segmentation_head=segmentation_head)
partial_ckpt_segmentation.restore(tf.train.latest_checkpoint(
save_dir)).expect_partial().assert_existing_objects_matched()
def test_forward(self, include_mask, training):
num_classes = 3
min_level = 3
max_level = 4
num_scales = 3
aspect_ratios = [1.0]
image_size = (256, 256)
images = np.random.rand(2, image_size[0], image_size[1], 3)
image_shape = np.array([[224, 100], [100, 224]])
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).multilevel_boxes
num_anchors_per_location = len(aspect_ratios) * num_scales
input_specs = tf.keras.layers.InputSpec(shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=min_level,
max_level=max_level,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(
min_level=min_level,
max_level=max_level,
num_anchors_per_location=num_anchors_per_location)
detection_head = instance_heads.DetectionHead(num_classes=num_classes)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
if include_mask:
mask_head = instance_heads.MaskHead(num_classes=num_classes,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(
crop_size=14)
else:
mask_head = None
mask_sampler_obj = None
mask_roi_aligner_obj = None
model = maskrcnn_model.MaskRCNNModel(backbone, decoder, rpn_head,
detection_head, roi_generator_obj,
roi_sampler_obj, roi_aligner_obj,
detection_generator_obj,
mask_head, mask_sampler_obj,
mask_roi_aligner_obj)
gt_boxes = np.array(
[[[10, 10, 15, 15], [2.5, 2.5, 7.5, 7.5], [-1, -1, -1, -1]],
[[100, 100, 150, 150], [-1, -1, -1, -1], [-1, -1, -1, -1]]],
dtype=np.float32)
gt_classes = np.array([[2, 1, -1], [1, -1, -1]], dtype=np.int32)
if include_mask:
gt_masks = np.ones((2, 3, 100, 100))
else:
gt_masks = None
results = model(images,
image_shape,
anchor_boxes,
gt_boxes,
gt_classes,
gt_masks,
training=training)
self.assertIn('rpn_boxes', results)
self.assertIn('rpn_scores', results)
if training:
self.assertIn('class_targets', results)
self.assertIn('box_targets', results)
self.assertIn('class_outputs', results)
self.assertIn('box_outputs', results)
if include_mask:
self.assertIn('mask_outputs', results)
else:
self.assertIn('detection_boxes', results)
self.assertIn('detection_scores', results)
self.assertIn('detection_classes', results)
self.assertIn('num_detections', results)
if include_mask:
self.assertIn('detection_masks', results)
def test_build_model(self,
use_separable_conv,
build_anchor_boxes,
shared_backbone,
shared_decoder,
is_training=True):
num_classes = 3
min_level = 3
max_level = 7
num_scales = 3
aspect_ratios = [1.0]
anchor_size = 3
resnet_model_id = 50
segmentation_resnet_model_id = 50
segmentation_output_stride = 16
aspp_dilation_rates = [6, 12, 18]
aspp_decoder_level = int(np.math.log2(segmentation_output_stride))
fpn_decoder_level = 3
num_anchors_per_location = num_scales * len(aspect_ratios)
image_size = 128
images = np.random.rand(2, image_size, image_size, 3)
image_shape = np.array([[image_size, image_size],
[image_size, image_size]])
shared_decoder = shared_decoder and shared_backbone
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=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])
else:
anchor_boxes = None
backbone = resnet.ResNet(model_id=resnet_model_id)
decoder = fpn.FPN(input_specs=backbone.output_specs,
min_level=min_level,
max_level=max_level,
use_separable_conv=use_separable_conv)
rpn_head = dense_prediction_heads.RPNHead(
min_level=min_level,
max_level=max_level,
num_anchors_per_location=num_anchors_per_location,
num_convs=1)
detection_head = instance_heads.DetectionHead(num_classes=num_classes)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
mask_head = instance_heads.MaskHead(num_classes=num_classes,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(crop_size=14)
if shared_backbone:
segmentation_backbone = None
else:
segmentation_backbone = resnet.ResNet(
model_id=segmentation_resnet_model_id)
if not shared_decoder:
level = aspp_decoder_level
segmentation_decoder = aspp.ASPP(
level=level, dilation_rates=aspp_dilation_rates)
else:
level = fpn_decoder_level
segmentation_decoder = None
segmentation_head = segmentation_heads.SegmentationHead(
num_classes=2, # stuff and common class for things,
level=level,
num_convs=2)
model = panoptic_maskrcnn_model.PanopticMaskRCNNModel(
backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
segmentation_backbone=segmentation_backbone,
segmentation_decoder=segmentation_decoder,
segmentation_head=segmentation_head,
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=anchor_size)
gt_boxes = np.array(
[[[10, 10, 15, 15], [2.5, 2.5, 7.5, 7.5], [-1, -1, -1, -1]],
[[100, 100, 150, 150], [-1, -1, -1, -1], [-1, -1, -1, -1]]],
dtype=np.float32)
gt_classes = np.array([[2, 1, -1], [1, -1, -1]], dtype=np.int32)
gt_masks = np.ones((2, 3, 100, 100))
# Results will be checked in test_forward.
_ = model(images,
image_shape,
anchor_boxes,
gt_boxes,
gt_classes,
gt_masks,
training=is_training)
def test_build_model(self,
use_separable_conv,
build_anchor_boxes,
shared_backbone,
shared_decoder,
is_training=True):
num_classes = 3
min_level = 2
max_level = 6
num_scales = 3
aspect_ratios = [1.0]
anchor_size = 3
resnet_model_id = 50
segmentation_resnet_model_id = 50
aspp_dilation_rates = [6, 12, 18]
aspp_decoder_level = 2
fpn_decoder_level = 2
num_anchors_per_location = num_scales * len(aspect_ratios)
image_size = 128
images = tf.random.normal([2, image_size, image_size, 3])
image_info = tf.convert_to_tensor([[[image_size, image_size],
[image_size, image_size], [1, 1],
[0, 0]],
[[image_size, image_size],
[image_size, image_size], [1, 1],
[0, 0]]])
shared_decoder = shared_decoder and shared_backbone
if build_anchor_boxes or not is_training:
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])
else:
anchor_boxes = None
backbone = resnet.ResNet(model_id=resnet_model_id)
decoder = fpn.FPN(input_specs=backbone.output_specs,
min_level=min_level,
max_level=max_level,
use_separable_conv=use_separable_conv)
rpn_head = dense_prediction_heads.RPNHead(
min_level=min_level,
max_level=max_level,
num_anchors_per_location=num_anchors_per_location,
num_convs=1)
detection_head = instance_heads.DetectionHead(num_classes=num_classes)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
panoptic_segmentation_generator_obj = panoptic_segmentation_generator.PanopticSegmentationGenerator(
output_size=[image_size, image_size],
max_num_detections=100,
stuff_classes_offset=90)
mask_head = instance_heads.MaskHead(num_classes=num_classes,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(crop_size=14)
if shared_backbone:
segmentation_backbone = None
else:
segmentation_backbone = resnet.ResNet(
model_id=segmentation_resnet_model_id)
if not shared_decoder:
feature_fusion = 'deeplabv3plus'
level = aspp_decoder_level
segmentation_decoder = aspp.ASPP(
level=level, dilation_rates=aspp_dilation_rates)
else:
feature_fusion = 'panoptic_fpn_fusion'
level = fpn_decoder_level
segmentation_decoder = None
segmentation_head = segmentation_heads.SegmentationHead(
num_classes=2, # stuff and common class for things,
level=level,
feature_fusion=feature_fusion,
decoder_min_level=min_level,
decoder_max_level=max_level,
num_convs=2)
model = panoptic_maskrcnn_model.PanopticMaskRCNNModel(
backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
panoptic_segmentation_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
segmentation_backbone=segmentation_backbone,
segmentation_decoder=segmentation_decoder,
segmentation_head=segmentation_head,
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=anchor_size)
gt_boxes = tf.convert_to_tensor(
[[[10, 10, 15, 15], [2.5, 2.5, 7.5, 7.5], [-1, -1, -1, -1]],
[[100, 100, 150, 150], [-1, -1, -1, -1], [-1, -1, -1, -1]]],
dtype=tf.float32)
gt_classes = tf.convert_to_tensor([[2, 1, -1], [1, -1, -1]],
dtype=tf.int32)
gt_masks = tf.ones((2, 3, 100, 100))
# Results will be checked in test_forward.
_ = model(images,
image_info,
anchor_boxes,
gt_boxes,
gt_classes,
gt_masks,
training=is_training)
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)
def test_build_model(self, include_mask, use_separable_conv,
build_anchor_boxes, is_training):
num_classes = 3
min_level = 3
max_level = 7
num_scales = 3
aspect_ratios = [1.0]
anchor_size = 3
resnet_model_id = 50
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=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])
else:
anchor_boxes = None
backbone = resnet.ResNet(model_id=resnet_model_id)
decoder = fpn.FPN(input_specs=backbone.output_specs,
min_level=min_level,
max_level=max_level,
use_separable_conv=use_separable_conv)
rpn_head = dense_prediction_heads.RPNHead(
min_level=min_level,
max_level=max_level,
num_anchors_per_location=num_anchors_per_location,
num_convs=1)
detection_head = instance_heads.DetectionHead(num_classes=num_classes)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_obj = roi_sampler.ROISampler()
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
if include_mask:
mask_head = instance_heads.MaskHead(num_classes=num_classes,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(
crop_size=14)
else:
mask_head = None
mask_sampler_obj = None
mask_roi_aligner_obj = None
model = maskrcnn_model.MaskRCNNModel(backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=anchor_size)
gt_boxes = np.array(
[[[10, 10, 15, 15], [2.5, 2.5, 7.5, 7.5], [-1, -1, -1, -1]],
[[100, 100, 150, 150], [-1, -1, -1, -1], [-1, -1, -1, -1]]],
dtype=np.float32)
gt_classes = np.array([[2, 1, -1], [1, -1, -1]], dtype=np.int32)
if include_mask:
gt_masks = np.ones((2, 3, 100, 100))
else:
gt_masks = None
# Results will be checked in test_forward.
_ = model(images,
image_shape,
anchor_boxes,
gt_boxes,
gt_classes,
gt_masks,
training=is_training)
def test_forward(self, strategy, training, shared_backbone,
shared_decoder):
num_classes = 3
min_level = 3
max_level = 4
num_scales = 3
aspect_ratios = [1.0]
anchor_size = 3
segmentation_resnet_model_id = 101
segmentation_output_stride = 16
aspp_dilation_rates = [6, 12, 18]
aspp_decoder_level = int(np.math.log2(segmentation_output_stride))
fpn_decoder_level = 3
class_agnostic_bbox_pred = False
cascade_class_ensemble = False
image_size = (256, 256)
images = np.random.rand(2, image_size[0], image_size[1], 3)
image_shape = np.array([[224, 100], [100, 224]])
shared_decoder = shared_decoder and shared_backbone
with strategy.scope():
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).multilevel_boxes
num_anchors_per_location = len(aspect_ratios) * num_scales
input_specs = tf.keras.layers.InputSpec(
shape=[None, None, None, 3])
backbone = resnet.ResNet(model_id=50, input_specs=input_specs)
decoder = fpn.FPN(min_level=min_level,
max_level=max_level,
input_specs=backbone.output_specs)
rpn_head = dense_prediction_heads.RPNHead(
min_level=min_level,
max_level=max_level,
num_anchors_per_location=num_anchors_per_location)
detection_head = instance_heads.DetectionHead(
num_classes=num_classes,
class_agnostic_bbox_pred=class_agnostic_bbox_pred)
roi_generator_obj = roi_generator.MultilevelROIGenerator()
roi_sampler_cascade = []
roi_sampler_obj = roi_sampler.ROISampler()
roi_sampler_cascade.append(roi_sampler_obj)
roi_aligner_obj = roi_aligner.MultilevelROIAligner()
detection_generator_obj = detection_generator.DetectionGenerator()
mask_head = instance_heads.MaskHead(num_classes=num_classes,
upsample_factor=2)
mask_sampler_obj = mask_sampler.MaskSampler(mask_target_size=28,
num_sampled_masks=1)
mask_roi_aligner_obj = roi_aligner.MultilevelROIAligner(
crop_size=14)
if shared_backbone:
segmentation_backbone = None
else:
segmentation_backbone = resnet.ResNet(
model_id=segmentation_resnet_model_id)
if not shared_decoder:
level = aspp_decoder_level
segmentation_decoder = aspp.ASPP(
level=level, dilation_rates=aspp_dilation_rates)
else:
level = fpn_decoder_level
segmentation_decoder = None
segmentation_head = segmentation_heads.SegmentationHead(
num_classes=2, # stuff and common class for things,
level=level,
num_convs=2)
model = panoptic_maskrcnn_model.PanopticMaskRCNNModel(
backbone,
decoder,
rpn_head,
detection_head,
roi_generator_obj,
roi_sampler_obj,
roi_aligner_obj,
detection_generator_obj,
mask_head,
mask_sampler_obj,
mask_roi_aligner_obj,
segmentation_backbone=segmentation_backbone,
segmentation_decoder=segmentation_decoder,
segmentation_head=segmentation_head,
class_agnostic_bbox_pred=class_agnostic_bbox_pred,
cascade_class_ensemble=cascade_class_ensemble,
min_level=min_level,
max_level=max_level,
num_scales=num_scales,
aspect_ratios=aspect_ratios,
anchor_size=anchor_size)
gt_boxes = np.array(
[[[10, 10, 15, 15], [2.5, 2.5, 7.5, 7.5], [-1, -1, -1, -1]],
[[100, 100, 150, 150], [-1, -1, -1, -1], [-1, -1, -1, -1]]],
dtype=np.float32)
gt_classes = np.array([[2, 1, -1], [1, -1, -1]], dtype=np.int32)
gt_masks = np.ones((2, 3, 100, 100))
results = model(images,
image_shape,
anchor_boxes,
gt_boxes,
gt_classes,
gt_masks,
training=training)
self.assertIn('rpn_boxes', results)
self.assertIn('rpn_scores', results)
if training:
self.assertIn('class_targets', results)
self.assertIn('box_targets', results)
self.assertIn('class_outputs', results)
self.assertIn('box_outputs', results)
self.assertIn('mask_outputs', results)
else:
self.assertIn('detection_boxes', results)
self.assertIn('detection_scores', results)
self.assertIn('detection_classes', results)
self.assertIn('num_detections', results)
self.assertIn('detection_masks', results)
self.assertIn('segmentation_outputs', results)
self.assertAllEqual([
2, image_size[0] // (2**level), image_size[1] // (2**level), 2
], results['segmentation_outputs'].numpy().shape)