def build_inputs(
self,
params: exp_cfg.DataConfig,
input_context: Optional[tf.distribute.InputContext] = None,
dataset_fn: Optional[dataset_fn_lib.PossibleDatasetType] = None
) -> tf.data.Dataset:
"""Build input dataset."""
decoder_cfg = params.decoder.get()
if params.decoder.type == 'simple_decoder':
decoder = tf_example_decoder.TfExampleDecoder(
include_mask=self._task_config.model.include_mask,
regenerate_source_id=decoder_cfg.regenerate_source_id,
mask_binarize_threshold=decoder_cfg.mask_binarize_threshold)
elif params.decoder.type == 'label_map_decoder':
decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap(
label_map=decoder_cfg.label_map,
include_mask=self._task_config.model.include_mask,
regenerate_source_id=decoder_cfg.regenerate_source_id,
mask_binarize_threshold=decoder_cfg.mask_binarize_threshold)
else:
raise ValueError('Unknown decoder type: {}!'.format(
params.decoder.type))
parser = maskrcnn_input.Parser(
output_size=self.task_config.model.input_size[:2],
min_level=self.task_config.model.min_level,
max_level=self.task_config.model.max_level,
num_scales=self.task_config.model.anchor.num_scales,
aspect_ratios=self.task_config.model.anchor.aspect_ratios,
anchor_size=self.task_config.model.anchor.anchor_size,
dtype=params.dtype,
rpn_match_threshold=params.parser.rpn_match_threshold,
rpn_unmatched_threshold=params.parser.rpn_unmatched_threshold,
rpn_batch_size_per_im=params.parser.rpn_batch_size_per_im,
rpn_fg_fraction=params.parser.rpn_fg_fraction,
aug_rand_hflip=params.parser.aug_rand_hflip,
aug_scale_min=params.parser.aug_scale_min,
aug_scale_max=params.parser.aug_scale_max,
aug_type=params.parser.aug_type,
skip_crowd_during_training=params.parser.
skip_crowd_during_training,
max_num_instances=params.parser.max_num_instances,
include_mask=self._task_config.model.include_mask,
mask_crop_size=params.parser.mask_crop_size)
if not dataset_fn:
dataset_fn = dataset_fn_lib.pick_dataset_fn(params.file_type)
reader = input_reader_factory.input_reader_generator(
params,
dataset_fn=dataset_fn,
decoder_fn=decoder.decode,
parser_fn=parser.parse_fn(params.is_training))
dataset = reader.read(input_context=input_context)
return dataset
def build_inputs(
self,
params: exp_cfg.DataConfig,
input_context: Optional[tf.distribute.InputContext] = None):
"""Build input dataset."""
if params.tfds_name:
decoder = tfds_factory.get_detection_decoder(params.tfds_name)
else:
decoder_cfg = params.decoder.get()
if params.decoder.type == 'simple_decoder':
decoder = tf_example_decoder.TfExampleDecoder(
regenerate_source_id=decoder_cfg.regenerate_source_id)
elif params.decoder.type == 'label_map_decoder':
decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap(
label_map=decoder_cfg.label_map,
regenerate_source_id=decoder_cfg.regenerate_source_id)
else:
raise ValueError('Unknown decoder type: {}!'.format(
params.decoder.type))
parser = retinanet_input.Parser(
output_size=self.task_config.model.input_size[:2],
min_level=self.task_config.model.min_level,
max_level=self.task_config.model.max_level,
num_scales=self.task_config.model.anchor.num_scales,
aspect_ratios=self.task_config.model.anchor.aspect_ratios,
anchor_size=self.task_config.model.anchor.anchor_size,
dtype=params.dtype,
match_threshold=params.parser.match_threshold,
unmatched_threshold=params.parser.unmatched_threshold,
aug_type=params.parser.aug_type,
aug_rand_hflip=params.parser.aug_rand_hflip,
aug_scale_min=params.parser.aug_scale_min,
aug_scale_max=params.parser.aug_scale_max,
skip_crowd_during_training=params.parser.
skip_crowd_during_training,
max_num_instances=params.parser.max_num_instances)
reader = input_reader_factory.input_reader_generator(
params,
dataset_fn=dataset_fn.pick_dataset_fn(params.file_type),
decoder_fn=decoder.decode,
parser_fn=parser.parse_fn(params.is_training))
dataset = reader.read(input_context=input_context)
return dataset
def build_inputs(self,
params: exp_cfg.DataConfig,
input_context: Optional[tf.distribute.InputContext] = None):
"""Build input dataset."""
if params.tfds_name:
decoder = tfds_factory.get_detection_decoder(params.tfds_name)
else:
decoder_cfg = params.decoder.get()
if params.decoder.type == 'simple_decoder':
decoder = tf_example_decoder.TfExampleDecoder(
regenerate_source_id=decoder_cfg.regenerate_source_id)
elif params.decoder.type == 'label_map_decoder':
decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap(
label_map=decoder_cfg.label_map,
regenerate_source_id=decoder_cfg.regenerate_source_id)
else:
raise ValueError('Unknown decoder type: {}!'.format(
params.decoder.type))
parser = centernet_input.CenterNetParser(
output_height=self.task_config.model.input_size[0],
output_width=self.task_config.model.input_size[1],
max_num_instances=self.task_config.model.max_num_instances,
bgr_ordering=params.parser.bgr_ordering,
channel_means=params.parser.channel_means,
channel_stds=params.parser.channel_stds,
aug_rand_hflip=params.parser.aug_rand_hflip,
aug_scale_min=params.parser.aug_scale_min,
aug_scale_max=params.parser.aug_scale_max,
aug_rand_hue=params.parser.aug_rand_hue,
aug_rand_brightness=params.parser.aug_rand_brightness,
aug_rand_contrast=params.parser.aug_rand_contrast,
aug_rand_saturation=params.parser.aug_rand_saturation,
odapi_augmentation=params.parser.odapi_augmentation,
dtype=params.dtype)
reader = input_reader.InputReader(
params,
dataset_fn=tf.data.TFRecordDataset,
decoder_fn=decoder.decode,
parser_fn=parser.parse_fn(params.is_training))
dataset = reader.read(input_context=input_context)
return dataset
def _get_data_decoder(self, params):
"""Get a decoder object to decode the dataset."""
if params.tfds_name:
decoder = tfds_factory.get_detection_decoder(params.tfds_name)
else:
decoder_cfg = params.decoder.get()
if params.decoder.type == 'simple_decoder':
self._coco_91_to_80 = decoder_cfg.coco91_to_80
decoder = tf_example_decoder.TfExampleDecoder(
coco91_to_80=decoder_cfg.coco91_to_80,
regenerate_source_id=decoder_cfg.regenerate_source_id)
elif params.decoder.type == 'label_map_decoder':
decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap(
label_map=decoder_cfg.label_map,
regenerate_source_id=decoder_cfg.regenerate_source_id)
else:
raise ValueError('Unknown decoder type: {}!'.format(
params.decoder.type))
return decoder
def test_result_shape(self, image_height, image_width, num_instances):
label_map_dir = self.get_temp_dir()
label_map_name = 'label_map.csv'
label_map_path = os.path.join(label_map_dir, label_map_name)
with open(label_map_path, 'w') as f:
f.write(LABEL_MAP_CSV_CONTENT)
decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap(
label_map_path, include_mask=True)
serialized_example = tfexample_utils.create_detection_test_example(
image_height=image_height,
image_width=image_width,
image_channel=3,
num_instances=num_instances).SerializeToString()
decoded_tensors = decoder.decode(
tf.convert_to_tensor(value=serialized_example))
results = tf.nest.map_structure(lambda x: x.numpy(), decoded_tensors)
self.assertAllEqual((image_height, image_width, 3),
results['image'].shape)
self.assertEqual(tfexample_utils.DUMP_SOURCE_ID, results['source_id'])
self.assertEqual(image_height, results['height'])
self.assertEqual(image_width, results['width'])
self.assertAllEqual((num_instances, ),
results['groundtruth_classes'].shape)
self.assertAllEqual((num_instances, ),
results['groundtruth_is_crowd'].shape)
self.assertAllEqual((num_instances, ),
results['groundtruth_area'].shape)
self.assertAllEqual((num_instances, 4),
results['groundtruth_boxes'].shape)
self.assertAllEqual((num_instances, image_height, image_width),
results['groundtruth_instance_masks'].shape)
self.assertAllEqual((num_instances, ),
results['groundtruth_instance_masks_png'].shape)
def build_inputs(
self,
params,
input_context: Optional[tf.distribute.InputContext] = None):
"""Build input dataset."""
if isinstance(params, coco.COCODataConfig):
dataset = coco.COCODataLoader(params).load(input_context)
else:
if params.tfds_name:
decoder = tfds_factory.get_detection_decoder(params.tfds_name)
else:
decoder_cfg = params.decoder.get()
if params.decoder.type == 'simple_decoder':
decoder = tf_example_decoder.TfExampleDecoder(
regenerate_source_id=decoder_cfg.regenerate_source_id)
elif params.decoder.type == 'label_map_decoder':
decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap(
label_map=decoder_cfg.label_map,
regenerate_source_id=decoder_cfg.regenerate_source_id)
else:
raise ValueError('Unknown decoder type: {}!'.format(
params.decoder.type))
parser = detr_input.Parser(
class_offset=self._task_config.losses.class_offset,
output_size=self._task_config.model.input_size[:2],
)
reader = input_reader_factory.input_reader_generator(
params,
dataset_fn=dataset_fn.pick_dataset_fn(params.file_type),
decoder_fn=decoder.decode,
parser_fn=parser.parse_fn(params.is_training))
dataset = reader.read(input_context=input_context)
return dataset
def test_result_content(self):
label_map_dir = self.get_temp_dir()
label_map_name = 'label_map.csv'
label_map_path = os.path.join(label_map_dir, label_map_name)
with open(label_map_path, 'w') as f:
f.write(LABEL_MAP_CSV_CONTENT)
decoder = tf_example_label_map_decoder.TfExampleDecoderLabelMap(
label_map_path, include_mask=True)
image_content = [[[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]],
[[0, 0, 0], [255, 255, 255], [255, 255, 255],
[0, 0, 0]],
[[0, 0, 0], [255, 255, 255], [255, 255, 255],
[0, 0, 0]],
[[0, 0, 0], [0, 0, 0], [0, 0, 0], [0, 0, 0]]]
image = tfexample_utils.encode_image(np.uint8(image_content),
fmt='PNG')
image_height = 4
image_width = 4
num_instances = 2
xmins = [0, 0.25]
xmaxs = [0.5, 1.0]
ymins = [0, 0]
ymaxs = [0.5, 1.0]
labels = [b'class_2', b'class_0']
areas = [
0.25 * image_height * image_width,
0.75 * image_height * image_width
]
is_crowds = [1, 0]
mask_content = [[[255, 255, 0, 0], [255, 255, 0, 0], [0, 0, 0, 0],
[0, 0, 0, 0]],
[[0, 255, 255, 255], [0, 255, 255, 255],
[0, 255, 255, 255], [0, 255, 255, 255]]]
masks = [
tfexample_utils.encode_image(np.uint8(m), fmt='PNG')
for m in list(mask_content)
]
serialized_example = tf.train.Example(features=tf.train.Features(
feature={
'image/encoded': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=[image]))),
'image/source_id': (tf.train.Feature(
bytes_list=tf.train.BytesList(
value=[tfexample_utils.DUMP_SOURCE_ID]))),
'image/height': (tf.train.Feature(
int64_list=tf.train.Int64List(value=[image_height]))),
'image/width': (tf.train.Feature(int64_list=tf.train.Int64List(
value=[image_width]))),
'image/object/bbox/xmin': (tf.train.Feature(
float_list=tf.train.FloatList(value=xmins))),
'image/object/bbox/xmax': (tf.train.Feature(
float_list=tf.train.FloatList(value=xmaxs))),
'image/object/bbox/ymin': (tf.train.Feature(
float_list=tf.train.FloatList(value=ymins))),
'image/object/bbox/ymax': (tf.train.Feature(
float_list=tf.train.FloatList(value=ymaxs))),
'image/object/class/text': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=labels))),
'image/object/is_crowd': (tf.train.Feature(
int64_list=tf.train.Int64List(value=is_crowds))),
'image/object/area': (tf.train.Feature(
float_list=tf.train.FloatList(value=areas))),
'image/object/mask': (tf.train.Feature(
bytes_list=tf.train.BytesList(value=masks))),
})).SerializeToString()
decoded_tensors = decoder.decode(
tf.convert_to_tensor(value=serialized_example))
results = tf.nest.map_structure(lambda x: x.numpy(), decoded_tensors)
self.assertAllEqual((image_height, image_width, 3),
results['image'].shape)
self.assertAllEqual(image_content, results['image'])
self.assertEqual(tfexample_utils.DUMP_SOURCE_ID, results['source_id'])
self.assertEqual(image_height, results['height'])
self.assertEqual(image_width, results['width'])
self.assertAllEqual((num_instances, ),
results['groundtruth_classes'].shape)
self.assertAllEqual((num_instances, ),
results['groundtruth_is_crowd'].shape)
self.assertAllEqual((num_instances, ),
results['groundtruth_area'].shape)
self.assertAllEqual((num_instances, 4),
results['groundtruth_boxes'].shape)
self.assertAllEqual((num_instances, image_height, image_width),
results['groundtruth_instance_masks'].shape)
self.assertAllEqual((num_instances, ),
results['groundtruth_instance_masks_png'].shape)
self.assertAllEqual([2, 0], results['groundtruth_classes'])
self.assertAllEqual([True, False], results['groundtruth_is_crowd'])
self.assertNDArrayNear([
0.25 * image_height * image_width,
0.75 * image_height * image_width
], results['groundtruth_area'], 1e-4)
self.assertNDArrayNear([[0, 0, 0.5, 0.5], [0, 0.25, 1.0, 1.0]],
results['groundtruth_boxes'], 1e-4)
self.assertNDArrayNear(mask_content,
results['groundtruth_instance_masks'], 1e-4)
self.assertAllEqual(masks, results['groundtruth_instance_masks_png'])