def test_yuv_color_transforms(self):
default_cfg = Detectron2GoRunner().get_default_cfg()
img = np.concatenate(
[
np.random.uniform(0, 1, size=(80, 60, 1)),
np.random.uniform(-0.5, 0.5, size=(80, 60, 1)),
np.random.uniform(-0.5, 0.5, size=(80, 60, 1)),
],
axis=2,
)
default_cfg.D2GO_DATA.AUG_OPS.TRAIN = [
'RandomContrastYUVOp::{"intensity_min": 0.3, "intensity_max": 0.5}',
]
low_contrast_tfm = build_transform_gen(default_cfg, is_train=True)
low_contrast, _ = apply_augmentations(low_contrast_tfm, img)
default_cfg.D2GO_DATA.AUG_OPS.TRAIN = [
'RandomSaturationYUVOp::{"intensity_min": 1.5, "intensity_max": 1.7}',
]
high_saturation_tfm = build_transform_gen(default_cfg, is_train=True)
high_saturation, _ = apply_augmentations(high_saturation_tfm, img)
# Use pixel statistics to roughly check transformed images as expected
# All channels have less variance
self.assertLess(np.var(low_contrast[:, :, 0]), np.var(img[:, :, 0]))
self.assertLess(np.var(low_contrast[:, :, 1]), np.var(img[:, :, 1]))
self.assertLess(np.var(low_contrast[:, :, 2]), np.var(img[:, :, 2]))
# 1st channel is unchanged (test w/ mean, var), 2nd + 3rd channels more variance
self.assertAlmostEqual(np.mean(high_saturation[:, :, 0]), np.mean(img[:, :, 0]))
self.assertAlmostEqual(np.var(high_saturation[:, :, 0]), np.var(img[:, :, 0]))
self.assertGreater(np.var(high_saturation[:, :, 1]), np.var(img[:, :, 1]))
self.assertGreater(np.var(high_saturation[:, :, 2]), np.var(img[:, :, 2]))
def test_build_transform_gen(self):
default_cfg = Detectron2GoRunner().get_default_cfg()
default_cfg.INPUT.MIN_SIZE_TRAIN = (30, )
default_cfg.INPUT.MIN_SIZE_TEST = 30
trans_train = build_transform_gen(default_cfg, is_train=True)
trans_test = build_transform_gen(default_cfg, is_train=False)
img = np.zeros((80, 60, 3))
trans_img_train, tl_train = apply_transform_gens(trans_train, img)
trans_img_test, tl_test = apply_transform_gens(trans_test, img)
self.assertEqual(trans_img_train.shape, (40, 30, 3))
self.assertEqual(trans_img_test.shape, (40, 30, 3))
def test_build_transform_gen_resize_square(self):
default_cfg = Detectron2GoRunner().get_default_cfg()
default_cfg.INPUT.MIN_SIZE_TRAIN = (30, )
default_cfg.INPUT.MIN_SIZE_TEST = 40
default_cfg.D2GO_DATA.AUG_OPS.TRAIN = ["ResizeShortestEdgeSquareOp"]
default_cfg.D2GO_DATA.AUG_OPS.TEST = ["ResizeShortestEdgeSquareOp"]
trans_train = build_transform_gen(default_cfg, is_train=True)
trans_test = build_transform_gen(default_cfg, is_train=False)
img = np.zeros((80, 60, 3))
trans_img_train, tl_train = apply_transform_gens(trans_train, img)
trans_img_test, tl_test = apply_transform_gens(trans_test, img)
self.assertEqual(trans_img_train.shape, (30, 30, 3))
self.assertEqual(trans_img_test.shape, (40, 40, 3))
def test_enlarge_bounding_box(self):
default_cfg = get_default_config()
default_cfg.D2GO_DATA.AUG_OPS.TRAIN = [
'EnlargeBoundingBoxOp::{"fixed_pad": 20}',
'EnlargeBoundingBoxOp::{"percentage": 0.2}',
]
enlarge_box_tfm = build_transform_gen(default_cfg, is_train=True)
boxes = np.array(
[[91, 46, 144, 111]],
dtype=np.float64,
)
transformed_bboxs = enlarge_box_tfm[0].apply_box(boxes)
expected_bboxs = np.array(
[[71, 26, 164, 131]],
dtype=np.float64,
)
err_msg = "transformed_bbox = {}, expected {}".format(
transformed_bboxs, expected_bboxs)
self.assertTrue(np.allclose(transformed_bboxs, expected_bboxs),
err_msg)
boxes = np.array(
[[91, 46, 144, 111]],
dtype=np.float64,
)
transformed_bboxs = enlarge_box_tfm[1].apply_box(boxes)
expected_bboxs = np.array(
[[85.7, 39.5, 149.3, 117.5]],
dtype=np.float64,
)
err_msg = "transformed_bbox = {}, expected {}".format(
transformed_bboxs, expected_bboxs)
self.assertTrue(np.allclose(transformed_bboxs, expected_bboxs),
err_msg)
dummy_data = np.array(
[[91, 46, 144, 111]],
dtype=np.float64,
)
dummy_data_out = enlarge_box_tfm[1].apply_image(dummy_data)
expected_out = np.array(
[[91, 46, 144, 111]],
dtype=np.float64,
)
err_msg = "Apply image failed"
self.assertTrue(np.allclose(dummy_data_out, expected_out), err_msg)
def get_mapper(cfg, is_train):
tfm_gens = build_transform_gen(cfg, is_train)
mapper = build_dataset_mapper(cfg, is_train, tfm_gens=tfm_gens)
return mapper
