def test_keypoint_jitter_does_not_change_img_mask_or_target(img_3x3, mask_3x3):
trf = slc.Stream([slt.KeypointsJitter(p=1, dx_range=(-0.2, 0.2), dy_range=(-0.2, 0.2))])
dc_res = trf({"image": img_3x3.copy(), "mask": mask_3x3.copy(), "label": 1}, return_torch=False)
assert np.array_equal(dc_res.data[0], img_3x3)
assert np.array_equal(dc_res.data[1], mask_3x3)
assert np.array_equal(dc_res.data[2], 1)
def test_keypoint_jitter_does_not_change_img_mask_or_target(img_3x3, mask_3x3):
dc = sld.DataContainer((img_3x3.copy(), mask_3x3.copy(), 1), 'IML')
trf = slc.Stream(
[slt.KeypointsJitter(p=1, dx_range=(-0.2, 0.2), dy_range=(-0.2, 0.2))])
dc_res = trf(dc)
assert np.array_equal(dc_res.data[0], img_3x3)
assert np.array_equal(dc_res.data[1], mask_3x3)
assert np.array_equal(dc_res.data[2], 1)
def test_keypoint_jitter_works_correctly(jitter_x, jitter_y, exp_x, exp_y):
kpts_data = np.array([[1, 1],]).reshape((1, 2))
kpts = slc.Keypoints(kpts_data.copy(), 2, 2)
dc = slc.DataContainer((kpts,), "P")
trf = slc.Stream([slt.KeypointsJitter(p=1, dx_range=(jitter_x, jitter_x), dy_range=(jitter_y, jitter_y))])
dc_res = trf(dc, return_torch=False)
assert np.array_equal(dc_res.data[0].data, np.array([exp_x, exp_y]).reshape((1, 2)))
def init_augs():
kvs = GlobalKVS()
args = kvs['args']
cutout = slt.ImageCutOut(cutout_size=(int(args.cutout * args.crop_x),
int(args.cutout * args.crop_y)),
p=0.5)
# plus-minus 1.3 pixels
jitter = slt.KeypointsJitter(dx_range=(-0.003, 0.003),
dy_range=(-0.003, 0.003))
ppl = tvt.Compose([
jitter if args.use_target_jitter else slc.Stream(),
slc.SelectiveStream([
slc.Stream([
slt.RandomFlip(p=0.5, axis=1),
slt.RandomProjection(affine_transforms=slc.Stream([
slt.RandomScale(range_x=(0.8, 1.3), p=1),
slt.RandomRotate(rotation_range=(-90, 90), p=1),
slt.RandomShear(
range_x=(-0.1, 0.1), range_y=(-0.1, 0.1), p=0.5),
]),
v_range=(1e-5, 2e-3),
p=0.5),
slt.RandomScale(range_x=(0.5, 2.5), p=0.5),
]),
slc.Stream()
],
probs=[0.7, 0.3]),
slc.Stream([
slt.PadTransform((args.pad_x, args.pad_y), padding='z'),
slt.CropTransform((args.crop_x, args.crop_y), crop_mode='r'),
]),
slc.SelectiveStream([
slt.ImageSaltAndPepper(p=1, gain_range=0.01),
slt.ImageBlur(p=1, blur_type='g', k_size=(3, 5)),
slt.ImageBlur(p=1, blur_type='m', k_size=(3, 5)),
slt.ImageAdditiveGaussianNoise(p=1, gain_range=0.5),
slc.Stream([
slt.ImageSaltAndPepper(p=1, gain_range=0.05),
slt.ImageBlur(p=0.5, blur_type='m', k_size=(3, 5)),
]),
slc.Stream([
slt.ImageBlur(p=0.5, blur_type='m', k_size=(3, 5)),
slt.ImageSaltAndPepper(p=1, gain_range=0.01),
]),
slc.Stream()
],
n=1),
slt.ImageGammaCorrection(p=0.5, gamma_range=(0.5, 1.5)),
cutout if args.use_cutout else slc.Stream(),
partial(solt2torchhm, downsample=None, sigma=None),
])
kvs.update('train_trf', ppl)
def get_landmark_transform_kneel(config):
cutout = slt.ImageCutOut(cutout_size=(int(config.dataset.cutout * config.dataset.augs.crop.crop_x),
int(config.dataset.cutout * config.dataset.augs.crop.crop_y)),
p=0.5)
# plus-minus 1.3 pixels
jitter = slt.KeypointsJitter(dx_range=(-0.003, 0.003), dy_range=(-0.003, 0.003))
ppl = transforms.Compose([
ColorPaddingWithSide(p=0.05, pad_size=10, side=SIDES.RANDOM, color=(50,100)),
TriangularMask(p=0.025, arm_lengths=(100, 50), side=SIDES.RANDOM, color=(50,100)),
TriangularMask(p=0.025, arm_lengths=(50, 100), side=SIDES.RANDOM, color=(50,100)),
LowVisibilityTransform(p=0.05, alpha=0.15, bgcolor=(50,100)),
SubSampleUpScale(p=0.01),
jitter if config.dataset.augs.use_target_jitter else slc.Stream(),
slc.SelectiveStream([
slc.Stream([
slt.RandomFlip(p=0.5, axis=1),
slt.RandomProjection(affine_transforms=slc.Stream([
slt.RandomScale(range_x=(0.9, 1.1), p=1),
slt.RandomRotate(rotation_range=(-90, 90), p=1),
slt.RandomShear(range_x=(-0.1, 0.1), range_y=(-0.1, 0.1), p=0.5),
]), v_range=(1e-5, 2e-3), p=0.5),
# slt.RandomScale(range_x=(0.5, 2.5), p=0.5),
]),
slc.Stream()
], probs=[0.7, 0.3]),
slc.Stream([
slt.PadTransform((config.dataset.augs.pad.pad_x, config.dataset.augs.pad.pad_y), padding='z'),
slt.CropTransform((config.dataset.augs.crop.crop_x, config.dataset.augs.crop.crop_y), crop_mode='r'),
]),
slc.SelectiveStream([
slt.ImageSaltAndPepper(p=1, gain_range=0.01),
slt.ImageBlur(p=1, blur_type='g', k_size=(3, 5)),
slt.ImageBlur(p=1, blur_type='m', k_size=(3, 5)),
slt.ImageAdditiveGaussianNoise(p=1, gain_range=0.5),
slc.Stream([
slt.ImageSaltAndPepper(p=1, gain_range=0.05),
slt.ImageBlur(p=0.5, blur_type='m', k_size=(3, 5)),
]),
slc.Stream([
slt.ImageBlur(p=0.5, blur_type='m', k_size=(3, 5)),
slt.ImageSaltAndPepper(p=1, gain_range=0.01),
]),
slc.Stream()
], n=1),
slt.ImageGammaCorrection(p=0.5, gamma_range=(0.5, 1.5)),
cutout if config.dataset.use_cutout else slc.Stream(),
partial(solt2torchhm, downsample=None, sigma=None),
])
return ppl