def test_custom_open_images_v4_object_detection():
validation_size = 0.2
batch_size = 1
image_size = [256, 128]
train_dataset = Dummy(batch_size=batch_size,
validation_size=validation_size,
pre_processor=ResizeWithGtBoxes(image_size))
validation_dataset = Dummy(batch_size=batch_size,
subset="validation",
validation_size=validation_size,
pre_processor=ResizeWithGtBoxes(image_size))
num_max_boxes = train_dataset.num_max_boxes
assert train_dataset.num_max_boxes == Dummy.count_max_boxes()
assert train_dataset.num_per_epoch == 10 * (1 - validation_size)
assert validation_dataset.num_per_epoch == 10 * (validation_size)
for _ in range(13):
images, labels = train_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_delta_mark_object_detection_has_validation_path():
batch_size = 4
image_size = [256, 128]
train_data_num = 3
validation_data_num = 2
train_dataset = setup_dataset(DummyObjectDetectionHasValidationPath,
subset="train",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
validation_dataset = setup_dataset(
DummyObjectDetectionHasValidationPath,
subset="validation",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
num_max_boxes = train_dataset.num_max_boxes
assert train_dataset.num_max_boxes == DummyObjectDetectionHasValidationPath.count_max_boxes(
)
assert validation_dataset.num_max_boxes == DummyObjectDetectionHasValidationPath.count_max_boxes(
)
assert train_dataset.num_per_epoch == train_data_num
assert validation_dataset.num_per_epoch == validation_data_num
for _ in range(2):
images, labels = train_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(2):
images, labels = validation_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_pascalvoc_2007_2012_no_skip_difficult():
batch_size = 3
image_size = [256, 512]
dataset = Pascalvoc20072012(
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
skip_difficult=False,
)
dataset = DatasetIterator(dataset)
num_max_boxes = 56
num_train_val_2007 = 2501 + 2510
num_train_val_2012 = 5717 + 5823
num_test_2007 = 4952
assert dataset.num_max_boxes == num_max_boxes
assert Pascalvoc20072012.count_max_boxes(
skip_difficult=False) == num_max_boxes
assert dataset.num_per_epoch == num_train_val_2007 + num_train_val_2012
val_dataset = Pascalvoc20072012(
subset="validation",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
skip_difficult=False)
val_dataset = DatasetIterator(val_dataset)
assert val_dataset.num_per_epoch == num_test_2007
for _ in range(STEP_SIZE):
images, labels = dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = val_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_mscoco_object_detection_person():
batch_size = 3
image_size = [256, 512]
num_max_boxes = 14
num_train = 38699
num_val = 18513
dataset = MscocoObjectDetectionPerson(
batch_size=batch_size, pre_processor=ResizeWithGtBoxes(image_size))
dataset = DatasetIterator(dataset)
assert MscocoObjectDetectionPerson.count_max_boxes() == num_max_boxes
assert dataset.num_max_boxes == num_max_boxes
assert dataset.num_per_epoch == num_train
val_dataset = MscocoObjectDetectionPerson(
subset="validation",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
val_dataset = DatasetIterator(val_dataset)
num_max_boxes = MscocoObjectDetectionPerson.count_max_boxes()
assert val_dataset.num_per_epoch == num_val
for _ in range(STEP_SIZE):
images, labels = dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = val_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_bdd100k():
batch_size = 3
image_size = [320, 320]
num_max_boxes = 100
num_train = 70000
num_val = 10000
dataset = BDD100K(batch_size=batch_size,
max_boxes=num_max_boxes,
pre_processor=ResizeWithGtBoxes(image_size))
dataset = DatasetIterator(dataset)
assert dataset.num_max_boxes == num_max_boxes
assert dataset.num_per_epoch == num_train
val_dataset = BDD100K(subset="validation",
batch_size=batch_size,
max_boxes=num_max_boxes,
pre_processor=ResizeWithGtBoxes(image_size))
val_dataset = DatasetIterator(val_dataset)
assert val_dataset.num_per_epoch == num_val
for _ in range(STEP_SIZE):
images, labels = dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = val_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_custom_has_validation_open_images_v4_object_detection():
batch_size = 8
image_size = [196, 128]
train_dataset = DummyHasValidation(subset="train", batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
train_dataset = DatasetIterator(train_dataset)
validation_dataset = DummyHasValidation(subset="validation", batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
validation_dataset = DatasetIterator(validation_dataset)
num_max_boxes = validation_dataset.num_max_boxes
assert validation_dataset.num_max_boxes == DummyHasValidation.count_max_boxes()
assert train_dataset.num_per_epoch == 10
assert validation_dataset.num_per_epoch == 16
assert len(train_dataset.classes) == 44
assert len(validation_dataset.classes) == 44
for _ in range(3):
images, labels = train_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(3):
images, labels = validation_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_widerface():
batch_size = 3
image_size = [160, 160]
num_max_boxes = 3
num_train = 7255
num_val = 1758
dataset = WiderFace(batch_size=batch_size,
max_boxes=num_max_boxes,
pre_processor=ResizeWithGtBoxes(image_size))
assert dataset.num_max_boxes == num_max_boxes
assert dataset.num_per_epoch == num_train
val_dataset = WiderFace(subset="validation",
batch_size=batch_size,
max_boxes=num_max_boxes,
pre_processor=ResizeWithGtBoxes(image_size))
assert val_dataset.num_per_epoch == num_val
for _ in range(STEP_SIZE):
images, labels = dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = val_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_training():
"""Test only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = YoloV2
config.DATASET_CLASS = LmThingsOnATable
config.IS_DEBUG = False
config.IMAGE_SIZE = [128, 160]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_STEPS = 1
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.IS_DISTRIBUTION = False
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.DATA_FORMAT = "NCHW"
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = ResizeWithGtBoxes(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
config.DATASET.DATA_FORMAT = "NCHW"
environment.init("test_yolo_v2")
prepare_dirs(recreate=True)
start_training(config)
def test_open_images_v4_object_detection():
batch_size = 1
image_size = [256, 256]
dataset = OpenImagesV4BoundingBox(batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
dataset = DatasetIterator(dataset)
num_max_boxes = dataset.num_max_boxes
assert dataset.num_max_boxes == OpenImagesV4BoundingBox.count_max_boxes()
for _ in range(5):
images, labels = dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_training():
"""Test only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = YoloV1
config.DATASET_CLASS = LmThingsOnATable
config.IS_DEBUG = False
config.IMAGE_SIZE = [70, 70]
config.BATCH_SIZE = 4
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.TASK = Tasks.OBJECT_DETECTION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = ResizeWithGtBoxes(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
environment.init("test_yolov_1")
prepare_dirs(recreate=True)
start_training(config)
def test_training():
"""Test only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = YoloV2
config.DATASET_CLASS = Pascalvoc2007
config.IS_DEBUG = False
config.IMAGE_SIZE = [128, 160]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.TASK = Tasks.OBJECT_DETECTION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.DATA_FORMAT = "NHWC"
# dataset config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = ResizeWithGtBoxes(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
config.DATASET.DATA_FORMAT = "NHWC"
environment.init("test_yolo_v2")
prepare_dirs(recreate=True)
start_training(config)
def test_pascalvoc_2012():
batch_size = 3
image_size = [256, 512]
dataset = Pascalvoc2012(batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
num_max_boxes = 39
dataset = DatasetIterator(dataset)
assert dataset.num_max_boxes == num_max_boxes
assert Pascalvoc2012.count_max_boxes() == num_max_boxes
assert dataset.num_per_epoch == 5717
val_dataset = Pascalvoc2012(subset="validation",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
val_dataset = DatasetIterator(val_dataset)
assert val_dataset.num_per_epoch == 5823
for _ in range(STEP_SIZE):
images, labels = dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = val_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_delta_mark_object_detection():
validation_size = 1 / 3
batch_size = 3
image_size = [256, 128]
all_data_num = 3
train_dataset = setup_dataset(DummyObjectDetectio,
subset="train",
validation_size=validation_size,
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
validation_dataset = setup_dataset(
DummyObjectDetectio,
subset="validation",
validation_size=validation_size,
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
num_max_boxes = train_dataset.num_max_boxes
assert train_dataset.num_max_boxes == DummyObjectDetectio.count_max_boxes()
assert validation_dataset.num_max_boxes == DummyObjectDetectio.count_max_boxes(
)
assert train_dataset.num_per_epoch == (1 - validation_size) * all_data_num
assert validation_dataset.num_per_epoch == validation_size * all_data_num
for _ in range(2):
images, labels = train_dataset.feed()
_show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_filp_top_bottom():
batch_size = 3
image_size = [256, 512]
dataset = LmThingsOnATable(
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
augmentor=FlipTopBottom(),
)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
def test_filp_left_right():
batch_size = 3
image_size = [256, 512]
dataset = LmThingsOnATable(
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
augmentor=FlipLeftRight(is_bounding_box=True),
)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
def test_contrast():
batch_size = 3
image_size = [256, 512]
dataset = LmThingsOnATable(
batch_size=batch_size, pre_processor=ResizeWithGtBoxes(image_size),
augmentor=Contrast((0.0, 2.0)),
)
dataset = DatasetIterator(dataset)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
def test_hue():
batch_size = 3
image_size = [256, 512]
dataset = Pascalvoc2007(
batch_size=batch_size, pre_processor=ResizeWithGtBoxes(image_size),
augmentor=Hue((-10, 10)),
)
dataset = DatasetIterator(dataset)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
def test_hue():
batch_size = 3
image_size = [256, 512]
dataset = LmThingsOnATable(
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
augmentor=Hue((-10, 10)),
)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
def test_filp_top_bottom():
batch_size = 3
image_size = [256, 512]
dataset = Pascalvoc2007(
batch_size=batch_size, pre_processor=ResizeWithGtBoxes(image_size),
augmentor=FlipTopBottom(),
)
dataset = DatasetIterator(dataset)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
def test_ssd_random_crop():
batch_size = 3
image_size = [256, 512]
dataset = LmThingsOnATable(
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
augmentor=SSDRandomCrop(),
)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
assert np.all(labels[:, :, 2] <= 512)
assert np.all(labels[:, :, 3] <= 256)
def test_ssd_random_crop():
batch_size = 3
image_size = [256, 512]
dataset = Pascalvoc2007(
batch_size=batch_size, pre_processor=ResizeWithGtBoxes(image_size),
augmentor=SSDRandomCrop(),
)
dataset = DatasetIterator(dataset)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
assert np.all(labels[:, :, 2] <= 512)
assert np.all(labels[:, :, 3] <= 256)
def test_sequence():
batch_size = 3
image_size = [256, 512]
augmentor = Sequence([
FlipLeftRight(),
FlipTopBottom(),
SSDRandomCrop(),
])
dataset = Pascalvoc2007(
batch_size=batch_size, pre_processor=ResizeWithGtBoxes(image_size),
augmentor=augmentor,
)
dataset = DatasetIterator(dataset)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
def test_sequence():
batch_size = 3
image_size = [256, 512]
augmentor = Sequence([
FlipLeftRight(is_bounding_box=True),
FlipTopBottom(is_bounding_box=True),
SSDRandomCrop(),
])
dataset = LmThingsOnATable(
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
augmentor=augmentor,
)
for _ in range(5):
images, labels = dataset.feed()
_show_images_with_boxes(images, labels)
def test_training():
"""Test only no error raised."""
config = EasyDict()
config.NETWORK_CLASS = YoloV2Quantize
config.DATASET_CLASS = Pascalvoc2007
config.IS_DEBUG = False
config.IMAGE_SIZE = [128, 160]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.TASK = Tasks.OBJECT_DETECTION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
config.NETWORK.ACTIVATION_QUANTIZER_KWARGS = {
'bit': 2,
'max_value': 2.0
}
config.NETWORK.WEIGHT_QUANTIZER = binary_channel_wise_mean_scaling_quantizer
config.NETWORK.WEIGHT_QUANTIZER_KWARGS = {}
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = ResizeWithGtBoxes(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
environment.init("test_yolov_2_quantize")
prepare_dirs(recreate=True)
start_training(config)
def test_lm_things_of_a_table():
batch_size = 3
image_size = [256, 512]
dataset = LmThingsOnATable(batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
num_max_boxes = LmThingsOnATable.count_max_boxes()
for _ in range(STEP_SIZE):
images, labels = dataset.feed()
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_pascalvoc_2007_with_target_classes():
batch_size = 3
image_size = [256, 512]
num_max_boxes = 12
num_train = 240
num_validation = 254
num_test = 433
assert TargetClassesPascalvoc2007.count_max_boxes() == num_max_boxes
dataset = TargetClassesPascalvoc2007(
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
)
dataset = DatasetIterator(dataset)
assert dataset.num_per_epoch == num_train
val_dataset = TargetClassesPascalvoc2007(
subset="validation",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
val_dataset = DatasetIterator(val_dataset)
assert val_dataset.num_per_epoch == num_validation
test_dataset = TargetClassesPascalvoc2007(
subset="test",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size))
test_dataset = DatasetIterator(test_dataset)
assert test_dataset.num_per_epoch == num_test
for _ in range(STEP_SIZE):
images, labels = dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = val_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = test_dataset.feed()
# _show_images_with_boxes(images, labels)
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
def test_pascalvoc_2007_not_skip_difficult():
batch_size = 3
image_size = [256, 512]
num_max_boxes = 42
num_train = 2501
num_validation = 2510
num_test = 4952
assert Pascalvoc2007.count_max_boxes(skip_difficult=False) == num_max_boxes
dataset = Pascalvoc2007(batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
skip_difficult=False)
dataset = DatasetIterator(dataset)
assert dataset.num_per_epoch == num_train
val_dataset = Pascalvoc2007(subset="validation",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
skip_difficult=False)
val_dataset = DatasetIterator(val_dataset)
assert val_dataset.num_per_epoch == num_validation
test_dataset = Pascalvoc2007(subset="test",
batch_size=batch_size,
pre_processor=ResizeWithGtBoxes(image_size),
skip_difficult=False)
test_dataset = DatasetIterator(test_dataset)
assert test_dataset.num_per_epoch == num_test
for _ in range(STEP_SIZE):
images, labels = dataset.feed()
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = val_dataset.feed()
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
for _ in range(STEP_SIZE):
images, labels = test_dataset.feed()
assert isinstance(images, np.ndarray)
assert images.shape[0] == batch_size
assert images.shape[1] == image_size[0]
assert images.shape[2] == image_size[1]
assert images.shape[3] == 3
assert isinstance(labels, np.ndarray)
assert labels.shape[0] == batch_size
assert labels.shape[1] == num_max_boxes
assert labels.shape[2] == 5
SUMMARISE_STEPS = 100
# for debug
# IS_DEBUG = True
# SUMMARISE_STEPS = 1
# SUMMARISE_STEPS = 100
# TEST_STEPS = 10000
# SUMMARISE_STEPS = 100
# pretrain
IS_PRETRAIN = False
PRETRAIN_VARS = []
PRETRAIN_DIR = ""
PRETRAIN_FILE = ""
PRE_PROCESSOR = Sequence([ResizeWithGtBoxes(size=IMAGE_SIZE), DivideBy255()])
anchors = [(1.3221, 1.73145), (3.19275, 4.00944), (5.05587, 8.09892),
(9.47112, 4.84053), (11.2364, 10.0071)]
score_threshold = 0.05
nms_iou_threshold = 0.5
nms_max_output_size = 100
POST_PROCESSOR = Sequence([
FormatYoloV2(
image_size=IMAGE_SIZE,
classes=CLASSES,
anchors=anchors,
data_format=DATA_FORMAT,
),
ExcludeLowScoreBox(threshold=score_threshold),
NMS(
iou_threshold=nms_iou_threshold,
# for debug
# IS_DEBUG = True
# SUMMARISE_STEPS = 1
# SUMMARISE_STEPS = 100
# TEST_STEPS = 10000
# SUMMARISE_STEPS = 100
# pretrain
IS_PRETRAIN = False
PRETRAIN_VARS = []
PRETRAIN_DIR = ""
PRETRAIN_FILE = ""
PRE_PROCESSOR = Sequence([
ResizeWithGtBoxes(size=IMAGE_SIZE),
DivideBy255()
])
anchors = [
(1.3221, 1.73145), (3.19275, 4.00944), (5.05587, 8.09892), (9.47112, 4.84053), (11.2364, 10.0071)
]
score_threshold = 0.05
nms_iou_threshold = 0.5
nms_max_output_size = 100
POST_PROCESSOR = Sequence([
FormatYoloV2(
image_size=IMAGE_SIZE,
classes=CLASSES,
anchors=anchors,
data_format=DATA_FORMAT,
),
SAVE_CHECKPOINT_STEPS = 1
KEEP_CHECKPOINT_MAX = 5
TEST_STEPS = 100
SUMMARISE_STEPS = 100
# distributed training
IS_DISTRIBUTION = False
# pretrain
IS_PRETRAIN = False
PRETRAIN_VARS = []
PRETRAIN_DIR = ""
PRETRAIN_FILE = ""
PRE_PROCESSOR = Sequence(
[ResizeWithGtBoxes(IMAGE_SIZE),
PerImageStandardization()])
anchors = [
(0.5, 0.25),
(1.0, 0.75),
]
POST_PROCESSOR = Sequence([
FormatYoloV2(
image_size=IMAGE_SIZE,
classes=CLASSES,
anchors=anchors,
data_format=DATA_FORMAT,
),
ExcludeLowScoreBox(threshold=0.05),
NMS(
