def test_yolov2_post_process():
tf.InteractiveSession()
image_size = [96, 64]
batch_size = 2
classes = range(5)
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)
def test_format_yolov2_shape():
image_size = [128, 96]
batch_size = 2
classes = range(8)
anchors = [(0.1, 0.2), (1.2, 1.1)]
post_process = FormatYoloV2(
image_size=image_size,
classes=classes,
anchors=anchors,
data_format="NCHW",
)
shape = (batch_size, len(anchors) * (len(classes) + 5), image_size[0]//32, image_size[1]//32)
output = np.random.uniform(-2., 2., size=shape).astype(np.float32)
y = post_process(output)["outputs"]
expected_shape = (batch_size, len(anchors) * len(classes) * image_size[0]//32 * image_size[1]//32, 6)
assert expected_shape == y.shape
# 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,
max_output_size=nms_max_output_size,
classes=CLASSES,
),
])
NETWORK = EasyDict()
NETWORK.OPTIMIZER_CLASS = tf.train.MomentumOptimizer
NETWORK.OPTIMIZER_KWARGS = {"momentum": 0.9}
NETWORK.LEARNING_RATE_FUNC = tf.train.piecewise_constant
# In the origianl yolov2 Paper, with a starting learning rate of 10−3, dividing it by 10 at 60 and 90 epochs.