def test_filp_left_right():
batch_size = 3
image_size = [256, 512]
dataset = Pascalvoc2007(
batch_size=batch_size, pre_processor=ResizeWithGtBoxes(image_size),
augmentor=FlipLeftRight(),
)
dataset = DatasetIterator(dataset)
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(),
)
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(),
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)
PRE_PROCESSOR = Sequence([Resize(size=IMAGE_SIZE), PerImageStandardization()])
POST_PROCESSOR = None
NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = tf.train.MomentumOptimizer
NETWORK.OPTIMIZER_KWARGS = {"momentum": 0.9}
NETWORK.LEARNING_RATE_FUNC = tf.train.piecewise_constant
NETWORK.LEARNING_RATE_KWARGS = {
"values": [0.1, 0.01, 0.001, 0.0001],
"boundaries": [40000, 60000, 80000],
}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.WEIGHT_DECAY_RATE = 0.0001
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}
# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
Pad(2),
Crop(size=IMAGE_SIZE),
FlipLeftRight(),
])
print("Shuffle {} train dataset with random state {}.".format(self.__class__.__name__, self.seed))
print(random_indices[0:10])
self.seed += 1
return random_indices
if __name__ == '__main__':
from lmnet.datasets.cifar10 import Cifar10
from lmnet.data_processor import Sequence
from lmnet.data_augmentor import FlipLeftRight, Hue, Blur
cifar10 = Cifar10()
augmentor = Sequence([
FlipLeftRight(0.5),
Hue((-10, 10)),
Blur(),
])
dataset_iterator = DatasetIterator(dataset=cifar10, enable_prefetch=True, augmentor=augmentor)
time.sleep(2)
import time
t0 = time.time()
data_batch = next(dataset_iterator)
t1 = time.time()
print("time of prefetch: {}".format(t1 - t0))
dataset_iterator2 = DatasetIterator(dataset=cifar10, enable_prefetch=False, augmentor=augmentor)
t0 = time.time()
data_batch = next(dataset_iterator2)
}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.ANCHORS = anchors
NETWORK.OBJECT_SCALE = 5.0
NETWORK.NO_OBJECT_SCALE = 1.0
NETWORK.CLASS_SCALE = 1.0
NETWORK.COORDINATE_SCALE = 1.0
NETWORK.LOSS_IOU_THRESHOLD = 0.6
NETWORK.WEIGHT_DECAY_RATE = 0.0005
NETWORK.SCORE_THRESHOLD = score_threshold
NETWORK.NMS_IOU_THRESHOLD = nms_iou_threshold
NETWORK.NMS_MAX_OUTPUT_SIZE = nms_max_output_size
NETWORK.SEEN_THRESHOLD = 8000
# dataset
DATASET = EasyDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
FlipLeftRight(is_bounding_box=True),
Brightness((0.75, 1.25)),
Color((0.75, 1.25)),
Contrast((0.75, 1.25)),
Hue((-10, 10)),
SSDRandomCrop(min_crop_ratio=0.7),
])
DATASET.ENABLE_PREFETCH = True
