def __init__(self):
self.solt_stream = slc.Stream(
[slt.Pad(pad_to=(512, 512), padding="r")])
def test_stream_empty(img, mask):
dc = slc.DataContainer((img, mask, 1), "IML")
stream = slc.Stream()
res = stream(dc, return_torch=False)
assert dc == res
def test_projection_empty_sampling_low_prob_trf():
trf = slt.RandomProjection(affine_transforms=slc.Stream(
[slt.RandomRotate(p=0)]),
p=1)
trf.sample_transform()
assert np.array_equal(trf.state_dict['transform_matrix'], np.eye(3))
def __init__(self):
self.imgaug_transform = iaa.Flipud(p=1)
self.augmentor_op = Operations.Flip(probability=1,
top_bottom_left_right="TOP_BOTTOM")
self.solt_stream = slc.Stream([slt.Flip(p=1, axis=0)])
def __init__(self):
self.imgaug_transform = iaa.CropToFixedSize(width=64, height=64)
self.augmentor_op = Operations.Crop(probability=1, width=64, height=64, centre=False)
self.solt_stream = slc.Stream([slt.CropTransform(crop_size=(64, 64), crop_mode="r")])
def __init__(self):
self.augmentor_op = Operations.Greyscale(probability=1)
self.imgaug_transform = iaa.Grayscale(alpha=1.0)
self.solt_stream = slc.Stream([slt.ImageColorTransform(mode="rgb2gs")])
def test_projection_empty_sampling_low_prob_trf(img_6x6_rgb):
dc = slc.DataContainer(img_6x6_rgb, "I")
trf = slt.Projection(affine_transforms=slc.Stream([slt.Rotate(p=0)]), p=1)
trf.sample_transform(dc)
assert np.array_equal(trf.state_dict["transform_matrix"], np.eye(3))
def __init__(self):
self.imgaug_transform = iaa.Add((127, 127), per_channel=False)
self.augmentor_op = Operations.RandomBrightness(probability=1, min_factor=1.5, max_factor=1.5)
self.solt_stream = slc.Stream([slt.ImageRandomBrightness(p=1, brightness_range=(127, 127))])
pass
dc = sld.DataContainer((data, kpts, 0), 'IPL')
stream = slc.Stream([
slt.RandomProjection(slc.Stream([
slt.RandomScale(range_x=(0.8, 1.1), p=1),
slt.RandomRotate(rotation_range=(-90, 90), p=1),
slt.RandomShear(range_x=(-0.2, 0.2), range_y=None, p=0.7),
]),
v_range=(1e-6, 3e-4),
p=1),
# Various cropping and padding tricks
slt.PadTransform(1000, 'z'),
slt.CropTransform(1000, crop_mode='c'),
slt.CropTransform(950, crop_mode='r'),
slt.PadTransform(1000, 'z'),
# Intensity augmentations
slt.ImageGammaCorrection(p=1, gamma_range=(0.5, 3)),
slc.SelectiveStream([
slc.SelectiveStream([
slt.ImageSaltAndPepper(p=1, gain_range=0.01),
slt.ImageBlur(p=0.5, blur_type='m', k_size=(11, )),
]),
slt.ImageAdditiveGaussianNoise(p=1, gain_range=0.5),
]),
])
for i in range(10):
res = stream(dc)
img_res, kp_c, lbl_c = res.data
@pytest.mark.parametrize(
"param_set",
[
{
"affine_transforms": "123"
},
{
"affine_transforms": 123
},
{
"affine_transforms": []
},
{
"affine_transforms": slc.Stream([
slt.Flip(),
])
},
{
"affine_transforms": slc.Stream([
slt.Flip(),
])
},
{
"v_range": "123"
},
{
"v_range": 123
},
{
"v_range": ("123", "456")
def test_reset_ignore_fast_mode_raises_error_for_streams_for_not_bool():
ppl = slc.Stream()
with pytest.raises(TypeError):
ppl.reset_ignore_fast_mode('123')
def test_stream_empty(img_2x2):
img = img_2x2
dc = slc.DataContainer((img, ), 'I')
stream = slc.Stream()
res, _, _ = stream(dc, return_torch=False)[0]
assert np.all(res == img)
def test_stream_with_zero_prob_transform(img, mask):
dc = slc.DataContainer((img, mask, 1), "IML")
stream = slc.Stream([slt.Rotate(p=0)])
res = stream(dc, return_torch=False)
assert dc == res
def __init__(self):
self.solt_stream = slc.Stream(
[slt.PadTransform(pad_to=(512, 512), padding='r')])
def train_test_transforms(conf, mean=None, std=None, crop_size=(512, 1024)):
"""
Compiles the different image augmentations that are used for input images.
:param conf: Transformation parameters
:param mean: Dataset image mean
:param std: Dataset image std
:param crop_size: Image size for the segmentation model
:return: Compiled transformation objects, and lists of the used transforms
"""
trf = conf['training']
prob = trf['transform_probability']
# Training transforms
# 3D transforms
if trf['experiment'] == '3D':
train_transforms = [
slc.SelectiveStream([
slc.Stream([
slt.RandomProjection(
slc.Stream([
slt.RandomRotate(rotation_range=tuple(
trf['rotation_range']),
p=prob),
slt.RandomScale(range_x=tuple(trf['scale_range']),
range_y=tuple(trf['scale_range']),
same=False,
p=prob),
#slt.RandomShear(range_x=tuple(trf['shear_range']),
# range_y=tuple(trf['shear_range']), p=prob),
slt.RandomTranslate(
range_x=trf['translation_range'],
range_y=trf['translation_range'],
p=prob)
]),
v_range=None #tuple(trf['v_range'])
),
# Spatial
slt.RandomFlip(p=prob),
slt.PadTransform(pad_to=crop_size),
slt.CropTransform(crop_mode='r', crop_size=crop_size),
# Intensity
# Brightness/contrast
slc.SelectiveStream([
slt.ImageRandomBrightness(brightness_range=tuple(
trf['brightness_range']),
p=prob),
slt.ImageRandomContrast(
contrast_range=trf['contrast_range'], p=prob)
]),
# Noise
slc.SelectiveStream([
slt.ImageSaltAndPepper(
p=prob, gain_range=trf['gain_range_sp']),
slt.ImageAdditiveGaussianNoise(
p=prob, gain_range=trf['gain_range_gn']),
slc.SelectiveStream([
slt.ImageBlur(p=prob,
blur_type='g',
k_size=(3, 7, 11),
gaussian_sigma=tuple(trf['sigma'])),
slt.ImageBlur(p=prob,
blur_type='m',
k_size=(3, 7, 11),
gaussian_sigma=tuple(trf['sigma']))
])
])
]),
# Empty stream
slc.Stream([
slt.PadTransform(pad_to=crop_size),
slt.CropTransform(crop_mode='r', crop_size=crop_size)
])
])
]
# 2D transforms
else:
train_transforms = [
slc.SelectiveStream([
slc.Stream([
# Projection
slt.RandomProjection(
slc.Stream([
slt.RandomRotate(rotation_range=tuple(
trf['rotation_range']),
p=prob),
slt.RandomScale(range_x=tuple(trf['scale_range']),
range_y=tuple(trf['scale_range']),
same=False,
p=prob),
# slt.RandomShear(range_x=tuple(trf['shear_range']),
# range_y=tuple(trf['shear_range']), p=prob),
slt.RandomTranslate(
range_x=trf['translation_range'],
range_y=trf['translation_range'],
p=prob)
]),
v_range=tuple(trf['v_range'])),
# Spatial
slt.RandomFlip(p=prob),
slt.PadTransform(pad_to=crop_size),
slt.CropTransform(crop_mode='r', crop_size=crop_size),
# Intensity
slc.SelectiveStream([
slt.ImageGammaCorrection(gamma_range=tuple(
trf['gamma_range']),
p=prob),
slt.ImageRandomHSV(h_range=tuple(trf['hsv_range']),
s_range=tuple(trf['hsv_range']),
v_range=tuple(trf['hsv_range']),
p=prob)
]),
slc.SelectiveStream([
slt.ImageRandomBrightness(brightness_range=tuple(
trf['brightness_range']),
p=prob),
slt.ImageRandomContrast(
contrast_range=trf['contrast_range'], p=prob)
]),
slc.SelectiveStream([
slt.ImageSaltAndPepper(
p=prob, gain_range=trf['gain_range_sp']),
slt.ImageAdditiveGaussianNoise(
p=prob, gain_range=trf['gain_range_gn']),
slc.SelectiveStream([
slt.ImageBlur(p=prob,
blur_type='g',
k_size=(3, 7, 11),
gaussian_sigma=tuple(trf['sigma'])),
slt.ImageBlur(p=prob,
blur_type='m',
k_size=(3, 7, 11),
gaussian_sigma=tuple(trf['sigma']))
])
])
]),
# Empty stream
slc.Stream([
slt.PadTransform(pad_to=crop_size),
slt.CropTransform(crop_mode='r', crop_size=crop_size)
])
])
]
# Compile training transforms
train_trf = [
# Move to SOLT format
wrap_solt,
# Transforms
slc.Stream(train_transforms),
# Extract image
unwrap_solt,
# Move to tensor
ApplyTransform(numpy2tens, (0, 1, 2))
]
# Validation transforms
val_trf = [
wrap_solt,
slc.Stream([
slt.PadTransform(pad_to=crop_size[1]),
slt.CropTransform(crop_mode='r', crop_size=crop_size)
]), unwrap_solt,
ApplyTransform(numpy2tens, idx=(0, 1, 2))
]
# Test transforms
test_trf = [unwrap_solt, ApplyTransform(numpy2tens, idx=(0, 1, 2))]
# Normalize train and val images if mean and std are given
if mean is not None and std is not None:
train_trf.append(
ApplyTransform(partial(normalize_channel_wise, mean=mean,
std=std)))
if mean is not None and std is not None:
val_trf.append(
ApplyTransform(partial(normalize_channel_wise, mean=mean,
std=std)))
# Compose transforms
train_trf_cmp = Compose(train_trf)
val_trf_cmp = Compose(val_trf)
test_trf_cmp = Compose(test_trf)
return {
'train': train_trf_cmp,
'val': val_trf_cmp,
'test': test_trf_cmp,
'train_list': train_trf,
'val_list': val_trf,
'test_list': test_trf
}
def __init__(self):
self.imgaug_transform = iaa.Affine(rotate=(45, 45), order=1, mode="reflect")
self.augmentor_op = Operations.RotateStandard(probability=1, max_left_rotation=45, max_right_rotation=45)
self.solt_stream = slc.Stream([slt.RandomRotate(p=1, rotation_range=(45, 45))], padding="r")
def test_stream_raises_assertion_error_when_not_basetransform_or_stream_in_the_transforms(
):
with pytest.raises(TypeError):
slc.Stream([1, 2, 3])
def __init__(self):
self.imgaug_transform = iaa.Multiply((1.5, 1.5), per_channel=False)
self.augmentor_op = Operations.RandomContrast(probability=1, min_factor=1.5, max_factor=1.5)
self.solt_stream = slc.Stream([slt.ImageRandomContrast(p=1, contrast_range=(1.5, 1.5))])
def test_stream_empty(img_2x2):
img = img_2x2
dc = sld.DataContainer((img, ), 'I')
stream = slc.Stream()
res, _, _ = stream(dc)[0]
assert np.all(res == img)
def __init__(self):
self.imgaug_transform = iaa.Scale(size=512, interpolation="linear")
self.solt_stream = slc.Stream([slt.ResizeTransform(resize_to=(512, 512))])
self.augmentor_op = Operations.Resize(probability=1, width=512, height=512, resample_filter="BILINEAR")
def init_transforms(mean_vector, std_vector):
kvs = GlobalKVS()
if mean_vector is not None:
mean_vector = torch.from_numpy(mean_vector).float()
std_vector = torch.from_numpy(std_vector).float()
norm_trf = partial(normalize_channel_wise,
mean=mean_vector,
std=std_vector)
norm_trf = partial(apply_by_index, transform=norm_trf, idx=[0, 1, 2])
else:
norm_trf = None
if kvs['args'].siamese:
resize_train = slc.Stream()
crop_train = slt.CropTransform(crop_size=(kvs['args'].imsize,
kvs['args'].imsize),
crop_mode='c')
else:
resize_train = slt.ResizeTransform(
(kvs['args'].inp_size, kvs['args'].inp_size))
crop_train = slt.CropTransform(crop_size=(kvs['args'].crop_size,
kvs['args'].crop_size),
crop_mode='r')
train_trf = [
wrap2solt,
slc.Stream([
slt.PadTransform(pad_to=(kvs['args'].imsize, kvs['args'].imsize)),
slt.CropTransform(crop_size=(kvs['args'].imsize,
kvs['args'].imsize),
crop_mode='c'),
resize_train,
slt.ImageAdditiveGaussianNoise(p=0.5, gain_range=0.3),
slt.RandomRotate(p=1, rotation_range=(-10, 10)),
crop_train,
slt.ImageGammaCorrection(p=0.5, gamma_range=(0.5, 1.5)),
]),
unpack_solt_data,
partial(pack_tensors, no_kl=kvs['args'].no_kl),
]
if not kvs['args'].siamese:
resize_val = slc.Stream([
slt.ResizeTransform((kvs['args'].inp_size, kvs['args'].inp_size)),
slt.CropTransform(crop_size=(kvs['args'].crop_size,
kvs['args'].crop_size),
crop_mode='c'),
])
else:
resize_val = slc.Stream()
val_trf = [
wrap2solt,
slc.Stream([
slt.PadTransform(pad_to=(kvs['args'].imsize, kvs['args'].imsize)),
slt.CropTransform(crop_size=(kvs['args'].imsize,
kvs['args'].imsize),
crop_mode='c'),
resize_val,
]),
unpack_solt_data,
partial(pack_tensors, no_kl=kvs['args'].no_kl),
]
if norm_trf is not None:
train_trf.append(norm_trf)
val_trf.append(norm_trf)
train_trf = transforms.Compose(train_trf)
val_trf = transforms.Compose(val_trf)
return train_trf, val_trf
trf.state_dict['translate_y']) == expected
@pytest.mark.parametrize('param_set', [
{
'affine_transforms': '123'
},
{
'affine_transforms': 123
},
{
'affine_transforms': []
},
{
'affine_transforms': slc.Stream([
slt.RandomFlip(),
])
},
{
'affine_transforms': slc.Stream([
slt.RandomFlip(),
])
},
{
'v_range': '123'
},
{
'v_range': 123
},
{
'v_range': [0, 0]
def init_transforms(nc=1):
if nc == 1:
norm_mean_std = Normalize((0.1307, ), (0.3081, ))
elif nc == 3:
norm_mean_std = Normalize((0.4914, 0.4822, 0.4465),
(0.247, 0.243, 0.261))
else:
raise ValueError("Not support channels of {}".format(nc))
train_trf = Compose([
wrap2solt,
slc.Stream([
slt.ResizeTransform(resize_to=(32, 32), interpolation='bilinear'),
slt.RandomScale(range_x=(0.9, 1.1), same=False, p=0.5),
slt.RandomFlip(axis=1, p=0.5),
# slt.RandomShear(range_x=(-0.05, 0.05), p=0.5),
# slt.RandomRotate(rotation_range=(-10, 10), p=0.5),
slt.RandomRotate(rotation_range=(-5, 5), p=0.5),
slt.PadTransform(pad_to=36),
slt.CropTransform(crop_size=32, crop_mode='r'),
slt.ImageAdditiveGaussianNoise(p=1.0)
]),
unpack_solt,
ApplyTransform(norm_mean_std)
])
test_trf = Compose([
wrap2solt,
slt.ResizeTransform(resize_to=(32, 32), interpolation='bilinear'),
unpack_solt,
ApplyTransform(norm_mean_std)
])
def custom_augment(img):
tr = Compose([
wrap2solt,
slc.Stream([
slt.ResizeTransform(resize_to=(32, 32),
interpolation='bilinear'),
slt.RandomScale(range_x=(0.9, 1.1), same=False, p=0.5),
slt.RandomFlip(axis=1, p=0.5),
# slt.RandomShear(range_x=(-0.05, 0.05), p=0.5),
# slt.RandomRotate(rotation_range=(-10, 10), p=0.5),
slt.RandomRotate(rotation_range=(-5, 5), p=0.5),
slt.PadTransform(pad_to=36),
slt.CropTransform(crop_size=32, crop_mode='r'),
slt.ImageAdditiveGaussianNoise(p=1.0)
]),
unpack_solt,
ApplyTransform(norm_mean_std)
])
if len(img.shape) == 3:
imgs = np.expand_dims(img, axis=0)
elif len(img.shape) == 4:
imgs = img
else:
raise ValueError('Expect num of dims 3 or 4, but got {}'.format(
len(img.shape)))
out_imgs = []
for b in range(imgs.shape[0]):
_img = imgs[b, :].astype(np.uint8)
_img, _ = tr((_img, 0))
out_imgs.append(_img)
return torch.stack(out_imgs, dim=0)
return train_trf, test_trf, custom_augment
def __init__(self):
self.imgaug_transform = iaa.Fliplr(p=1)
self.augmentor_op = Operations.Flip(probability=1,
top_bottom_left_right="LEFT_RIGHT")
self.solt_stream = slc.Stream([slt.Flip(p=1, axis=1)])
os.path.join(args.snapshots, 'mean_std.npy'))
elif args.color_space == 'yuv':
mean_vector, std_vector = np.load(
os.path.join(args.snapshots, 'mean_std_yuv.npy'))
else:
raise NotImplementedError
norm_trf = tv_transforms.Normalize(
torch.from_numpy(mean_vector).float(),
torch.from_numpy(std_vector).float())
eval_trf = tv_transforms.Compose([
img_labels2solt,
slc.Stream([
slt.PadTransform(pad_to=(PAD_TO, PAD_TO)),
slt.CropTransform(crop_size=(CROP_SIZE, CROP_SIZE),
crop_mode='c'), # center crop
]),
unpack_solt_data,
partial(apply_by_index, transform=tv_transforms.ToTensor(), idx=0),
partial(apply_by_index, transform=norm_trf, idx=0)
])
dataset, dataset_length = init_dataset(args.dataset_root,
args.dataset_name,
batch='test')
metadata = pd.read_csv(
os.path.join(args.metadata_root, args.dataset_name, 'test_meta.csv'))
eval_dataset = ImageClassificationDataset(dataset, metadata,
def __init__(self):
self.imgaug_transform = iaa.AddToHueAndSaturation((20, 20),
per_channel=False)
self.solt_stream = slc.Stream([
slt.HSV(p=1, h_range=(20, 20), s_range=(20, 20), v_range=(20, 20))
])
{
"cutout": {
"cutout_size": 2,
"p": 0.5
}
},
],
},
},
]
}
},
slc.Stream([
slt.Pad(34),
slt.Crop(32, "r"),
slt.CutOut(2),
slc.Stream([slt.Pad(34),
slt.Crop(32, "r"),
slt.CutOut(2)]),
]),
],
[
{
"stream": {
"transforms": [
{
"stream": {
"interpolation":
None,
"padding":
None,
"transforms": [
def __init__(self):
self.solt_stream = slc.Stream(
[slt.GammaCorrection(p=1, gamma_range=(0.5, 0.5))])
def test_projection_empty_sampling_no_trf(img):
dc = slc.DataContainer(img, "I")
trf = slt.Projection(affine_transforms=slc.Stream(), p=1)
trf.sample_transform(dc)
assert np.array_equal(trf.state_dict["transform_matrix"], np.eye(3))