def test_exclude_low_score_box():
threshold = 0.35
inputs = np.array([
[
[10, 11, 12, 13, 1, 0.1],
[20, 21, 22, 23, 2, 0.2],
],
[
[30, 31, 32, 33, 3, 0.3],
[40, 41, 42, 43, 4, 0.4],
],
[
[50, 51, 52, 53, 5, 0.5],
[60, 61, 62, 63, 6, 0.6],
],
])
expected_ys = [
np.zeros([0, 6]),
np.array([
[40, 41, 42, 43, 4, 0.4],
]),
np.array([
[50, 51, 52, 53, 5, 0.5],
[60, 61, 62, 63, 6, 0.6],
]),
]
post_process = ExcludeLowScoreBox(threshold=threshold, )
ys = post_process(inputs)["outputs"]
for expected_y, y in zip(expected_ys, ys):
assert np.allclose(expected_y, y)
def test_yolov2_post_process():
tf.InteractiveSession()
image_size = [96, 64]
batch_size = 2
classes = Pascalvoc2007.classes
anchors = [(0.1, 0.2), (1.2, 1.1)]
data_format = "NHWC"
score_threshold = 0.25
nms_iou_threshold = 0.5
model = YoloV2(
image_size=image_size,
batch_size=batch_size,
classes=classes,
anchors=anchors,
data_format=data_format,
score_threshold=score_threshold,
nms_iou_threshold=nms_iou_threshold,
)
post_process = Sequence([
FormatYoloV2(
image_size=image_size,
classes=classes,
anchors=anchors,
data_format=data_format,
),
ExcludeLowScoreBox(threshold=score_threshold),
NMS(
iou_threshold=nms_iou_threshold,
classes=classes,
),
])
shape = (batch_size, len(anchors) * (len(classes) + 5),
image_size[0] // 32, image_size[1] // 32)
np_output = np.random.uniform(-2., 2., size=shape).astype(np.float32)
output = tf.constant(np_output)
ys = model.post_process(output)
expected_ys = post_process(outputs=np_output)["outputs"]
for y, expected_y in zip(ys, expected_ys):
assert np.allclose(y.eval(), expected_y), (y.eval(), expected_y)
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,
max_output_size=nms_max_output_size,
classes=CLASSES,
),
])
NETWORK = SmartDict()
NETWORK.OPTIMIZER_CLASS = tf.compat.v1.train.MomentumOptimizer
NETWORK.OPTIMIZER_KWARGS = {"momentum": 0.9}
NETWORK.LEARNING_RATE_FUNC = tf.compat.v1.train.piecewise_constant
_epoch_steps = 16551 // BATCH_SIZE
NETWORK.LEARNING_RATE_KWARGS = {
"values": [1e-6, 1e-4, 1e-5, 1e-6, 1e-7],
"boundaries":
TFDS_PRE_PROCESSOR = TFDSProcessorSequence(
[TFDSResizeWithGtBoxes(IMAGE_SIZE),
TFDSPerImageStandardization()])
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(
iou_threshold=0.5,
classes=CLASSES,
),
])
NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
NETWORK.IMAGE_SIZE = IMAGE_SIZE
NETWORK.BATCH_SIZE = BATCH_SIZE
NETWORK.DATA_FORMAT = DATA_FORMAT
NETWORK.ANCHORS = anchors
NETWORK.WEIGHT_DECAY_RATE = 0.0005
NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer