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)
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.LOSS_WARMUP_STEPS = 1280 // BATCH_SIZE
# quantization
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2.0}
NETWORK.WEIGHT_QUANTIZER = binary_channel_wise_mean_scaling_quantizer
NETWORK.WEIGHT_QUANTIZER_KWARGS = {}
NETWORK.QUANTIZE_FIRST_CONVOLUTION = True
NETWORK.QUANTIZE_LAST_CONVOLUTION = False
# dataset
DATASET = SmartDict()
DATASET.BATCH_SIZE = BATCH_SIZE
DATASET.DATA_FORMAT = DATA_FORMAT
DATASET.PRE_PROCESSOR = PRE_PROCESSOR
DATASET.AUGMENTOR = Sequence([
FlipLeftRight(),
Brightness((0.75, 1.25)),
Color((0.75, 1.25)),
Contrast((0.75, 1.25)),
Hue((-10, 10)),
SSDRandomCrop(min_crop_ratio=0.7),
])