def build_transform(self):
"""
Creates a basic transformation that was used to train the models
"""
cfg = self.cfg
# we are loading images with OpenCV, so we don't need to convert them
# to BGR, they are already! So all we need to do is to normalize
# by 255 if we want to convert to BGR255 format, or flip the channels
# if we want it to be in RGB in [0-1] range.
if cfg.INPUT.TO_BGR255:
to_bgr_transform = T.Lambda(lambda x: x * 255)
else:
to_bgr_transform = T.Lambda(lambda x: x[[2, 1, 0]])
normalize_transform = T.ImageNormalize(
mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD
)
min_size = cfg.INPUT.MIN_SIZE_TEST
max_size = cfg.INPUT.MAX_SIZE_TEST
transform = T.Compose(
[
T.ToPILImage(),
Resize(min_size, max_size),
T.ToTensor(),
to_bgr_transform,
normalize_transform,
]
)
return transform
def get_transform(params, gray=False, mask=False):
transform_ = []
# resize
transform_.append(
transform.Resize((params['load_h'], params['load_w']), Image.BICUBIC))
# flip
if params['flip']:
transform_.append(transform.Lambda(lambda img: transform.hflip(img)))
if gray:
transform_.append(transform.Gray())
if mask:
transform_.append(transform.ImageNormalize([
0.,
], [
1.,
]))
else:
if not gray:
transform_.append(
transform.ImageNormalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]))
else:
transform_.append(transform.ImageNormalize([
0.5,
], [
0.5,
]))
return transform.Compose(transform_)
def build_transform():
if cfg.INPUT.TO_BGR255:
to_bgr_transform = T.Lambda(lambda x: x * 255)
else:
to_bgr_transform = T.Lambda(lambda x: x[[2, 1, 0]])
normalize_transform = T.Normalize(mean=cfg.INPUT.PIXEL_MEAN,
std=cfg.INPUT.PIXEL_STD)
min_size = cfg.INPUT.MIN_SIZE_TEST
max_size = cfg.INPUT.MAX_SIZE_TEST
transform = T.Compose([
T.ToPILImage(),
Resize(min_size, max_size),
T.ToTensor(),
to_bgr_transform,
normalize_transform,
])
return transform
def test_lambda(self):
trans = transform.Lambda(lambda x: x.add(10))
x = jt.random([10])
y = trans(x)
self.assertTrue(np.allclose(y.data, jt.add(x, 10).data))