diff --git a/MANIFEST.in b/MANIFEST.in
index dc8f75ecc362021410f6686954b25c1d98966bc8..cf1d827b4de456cfd9faa016ac18001948a7caf3 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,3 +1,3 @@
include README.rst buildout.cfg COPYING version.txt requirements.txt
recursive-include doc *.rst *.png *.ico *.txt
-recursive-include bob *.json
+recursive-include bob *.json *.png
diff --git a/bob/ip/binseg/data/transforms.py b/bob/ip/binseg/data/transforms.py
index a347fcbb3af00052ea79dc7394a2945a006986e1..bea81bcd9dbf7ba998795f96c35ccae3b7c1b417 100644
--- a/bob/ip/binseg/data/transforms.py
+++ b/bob/ip/binseg/data/transforms.py
@@ -18,8 +18,6 @@ import PIL.Image
import torchvision.transforms
import torchvision.transforms.functional
-import bob.core
-
class TupleMixin:
"""Adds support to work with tuples of objects to torchvision transforms"""
@@ -104,12 +102,17 @@ class SingleAutoLevel16to8:
To auto-level, we calculate the maximum and the minimum of the image, and
consider such a range should be mapped to the [0,255] range of the
destination image.
+
"""
def __call__(self, img):
+ imin, imax = img.getextrema()
+ irange = imax - imin
return PIL.Image.fromarray(
- bob.core.convert(img, "uint8", (0, 255), img.getextrema())
- )
+ numpy.round(
+ 255.0 * (numpy.array(img).astype(float) - imin) / irange
+ ).astype("uint8"),
+ ).convert("L")
class AutoLevel16to8(TupleMixin, SingleAutoLevel16to8):
@@ -121,6 +124,7 @@ class AutoLevel16to8(TupleMixin, SingleAutoLevel16to8):
consider such a range should be mapped to the [0,255] range of the
destination image.
"""
+
pass
@@ -132,6 +136,7 @@ class SingleToRGB:
defaults. This may be aggressive if applied to 16-bit images without
further considerations.
"""
+
def __call__(self, img):
return img.convert(mode="RGB")
@@ -195,8 +200,8 @@ class RandomRotation(torchvision.transforms.RandomRotation):
"""
def __init__(self, p=0.5, **kwargs):
- kwargs.setdefault('degrees', 15)
- kwargs.setdefault('resample', PIL.Image.BILINEAR)
+ kwargs.setdefault("degrees", 15)
+ kwargs.setdefault("resample", PIL.Image.BILINEAR)
super(RandomRotation, self).__init__(**kwargs)
self.p = p
@@ -205,16 +210,17 @@ class RandomRotation(torchvision.transforms.RandomRotation):
if random.random() < self.p:
angle = self.get_params(self.degrees)
return [
- torchvision.transforms.functional.rotate(img, angle,
- self.resample, self.expand, self.center)
+ torchvision.transforms.functional.rotate(
+ img, angle, self.resample, self.expand, self.center
+ )
for img in args
- ]
+ ]
else:
return args
def __repr__(self):
retval = super(RandomRotation, self).__repr__()
- return retval.replace('(', f'(p={self.p},', 1)
+ return retval.replace("(", f"(p={self.p},", 1)
class ColorJitter(torchvision.transforms.ColorJitter):
@@ -243,10 +249,10 @@ class ColorJitter(torchvision.transforms.ColorJitter):
"""
def __init__(self, p=0.5, **kwargs):
- kwargs.setdefault('brightness', 0.3)
- kwargs.setdefault('contrast', 0.3)
- kwargs.setdefault('saturation', 0.02)
- kwargs.setdefault('hue', 0.02)
+ kwargs.setdefault("brightness", 0.3)
+ kwargs.setdefault("contrast", 0.3)
+ kwargs.setdefault("saturation", 0.02)
+ kwargs.setdefault("hue", 0.02)
super(ColorJitter, self).__init__(**kwargs)
self.p = p
@@ -259,4 +265,4 @@ class ColorJitter(torchvision.transforms.ColorJitter):
def __repr__(self):
retval = super(ColorJitter, self).__repr__()
- return retval.replace('(', f'(p={self.p},', 1)
+ return retval.replace("(", f"(p={self.p},", 1)
diff --git a/bob/ip/binseg/test/test_transforms.py b/bob/ip/binseg/test/test_transforms.py
index 826343f632d9c4e7b62fbecea68df45bcf71728b..a1967fe54894eccd1fe818c8564c08d92c98ad88 100644
--- a/bob/ip/binseg/test/test_transforms.py
+++ b/bob/ip/binseg/test/test_transforms.py
@@ -4,7 +4,10 @@
import random
import nose.tools
+import pkg_resources
+
import numpy
+import PIL.Image
import torch
import torchvision.transforms.functional
@@ -93,7 +96,7 @@ def test_pad_default():
# checks that the border introduced with padding is all about "fill"
img_t = numpy.array(img_t)
img_t[idx] = 0
- border_size_plane = (img_t[:,:,0].size - numpy.array(img)[:,:,0].size)
+ border_size_plane = img_t[:, :, 0].size - numpy.array(img)[:, :, 0].size
nose.tools.eq_(img_t.sum(), 0)
gt_t = numpy.array(gt_t)
@@ -131,8 +134,8 @@ def test_pad_2tuple():
# checks that the border introduced with padding is all about "fill"
img_t = numpy.array(img_t)
img_t[idx] = 0
- border_size_plane = (img_t[:,:,0].size - numpy.array(img)[:,:,0].size)
- expected_sum = sum((fill[k]*border_size_plane) for k in range(3))
+ border_size_plane = img_t[:, :, 0].size - numpy.array(img)[:, :, 0].size
+ expected_sum = sum((fill[k] * border_size_plane) for k in range(3))
nose.tools.eq_(img_t.sum(), expected_sum)
gt_t = numpy.array(gt_t)
@@ -170,8 +173,8 @@ def test_pad_4tuple():
# checks that the border introduced with padding is all about "fill"
img_t = numpy.array(img_t)
img_t[idx] = 0
- border_size_plane = (img_t[:,:,0].size - numpy.array(img)[:,:,0].size)
- expected_sum = sum((fill[k]*border_size_plane) for k in range(3))
+ border_size_plane = img_t[:, :, 0].size - numpy.array(img)[:, :, 0].size
+ expected_sum = sum((fill[k] * border_size_plane) for k in range(3))
nose.tools.eq_(img_t.sum(), expected_sum)
gt_t = numpy.array(gt_t)
@@ -194,7 +197,7 @@ def test_resize_downscale_w():
img, gt, mask = [_create_img(im_size) for i in range(3)]
nose.tools.eq_(img.size, (im_size[2], im_size[1])) # confirms the above
img_t, gt_t, mask_t = transforms(img, gt, mask)
- new_size = (new_size, (new_size*im_size[1])/im_size[2])
+ new_size = (new_size, (new_size * im_size[1]) / im_size[2])
nose.tools.eq_(img_t.size, new_size)
nose.tools.eq_(gt_t.size, new_size)
nose.tools.eq_(mask_t.size, new_size)
@@ -224,8 +227,8 @@ def test_crop():
# test
idx = (
- slice(crop_size[0], crop_size[0]+crop_size[2]),
- slice(crop_size[1], crop_size[1]+crop_size[3]),
+ slice(crop_size[0], crop_size[0] + crop_size[2]),
+ slice(crop_size[1], crop_size[1] + crop_size[3]),
slice(0, im_size[0]),
)
transforms = Crop(*crop_size)
@@ -297,7 +300,7 @@ def test_rotation():
assert numpy.any(numpy.array(img1_t) != numpy.array(img))
# asserts two random transforms are not the same
- img_t2, = transforms(img)
+ (img_t2,) = transforms(img)
assert numpy.any(numpy.array(img_t2) != numpy.array(img1_t))
@@ -327,15 +330,40 @@ def test_color_jitter():
def test_compose():
- transforms = Compose([
- RandomVerticalFlip(p=1),
- RandomHorizontalFlip(p=1),
- RandomVerticalFlip(p=1),
- RandomHorizontalFlip(p=1),
- ])
+ transforms = Compose(
+ [
+ RandomVerticalFlip(p=1),
+ RandomHorizontalFlip(p=1),
+ RandomVerticalFlip(p=1),
+ RandomHorizontalFlip(p=1),
+ ]
+ )
img, gt, mask = [_create_img((3, 24, 42)) for i in range(3)]
img_t, gt_t, mask_t = transforms(img, gt, mask)
assert numpy.all(numpy.array(img_t) == numpy.array(img))
assert numpy.all(numpy.array(gt_t) == numpy.array(gt))
assert numpy.all(numpy.array(mask_t) == numpy.array(mask))
+
+
+def test_16bit_autolevel():
+
+ test_image_path = pkg_resources.resource_filename(
+ __name__, "testimg-16bit.png"
+ )
+ # the way to load a 16-bit PNG image correctly, according to:
+ # https://stackoverflow.com/questions/32622658/read-16-bit-png-image-file-using-python
+ # https://github.com/python-pillow/Pillow/issues/3011
+ img = PIL.Image.fromarray(
+ numpy.array(
+ PIL.Image.open("bob/ip/binseg/test/testimg-16bit.png")
+ ).astype("uint16")
+ )
+ nose.tools.eq_(img.mode, "I;16")
+ nose.tools.eq_(img.getextrema(), (0, 65281))
+
+ timg = SingleAutoLevel16to8()(img)
+ nose.tools.eq_(timg.mode, "L")
+ nose.tools.eq_(timg.getextrema(), (0, 255))
+ #timg.show()
+ #import ipdb; ipdb.set_trace()
diff --git a/bob/ip/binseg/test/testimg-16bit.png b/bob/ip/binseg/test/testimg-16bit.png
new file mode 100644
index 0000000000000000000000000000000000000000..1bd5c6ad984e9200e0611d492149126b628fd74d
Binary files /dev/null and b/bob/ip/binseg/test/testimg-16bit.png differ
diff --git a/conda/meta.yaml b/conda/meta.yaml
index a6e591aa6c590bb61dc4358b47d830c65b03cc2b..b0b78dc569dc0490873f3a81547e3def158661f3 100644
--- a/conda/meta.yaml
+++ b/conda/meta.yaml
@@ -25,21 +25,21 @@ requirements:
host:
- python {{ python }}
- setuptools {{ setuptools }}
- - torchvision {{ torchvision }} # [linux]
- - pytorch {{ pytorch }} # [linux]
- numpy {{ numpy }}
+ - h5py {{ h5py }}
+ - pytorch {{ pytorch }} # [linux]
+ - torchvision {{ torchvision }} # [linux]
- bob.extension
- - bob.core
- - bob.io.base
run:
- python
- setuptools
+ - {{ pin_compatible('numpy') }}
+ - {{ pin_compatible('pillow') }}
+ - {{ pin_compatible('pandas') }}
+ - {{ pin_compatible('matplotlib') }}
- {{ pin_compatible('pytorch') }} # [linux]
- {{ pin_compatible('torchvision') }} # [linux]
- - {{ pin_compatible('numpy') }}
- - pandas
- - pillow
- - matplotlib
+ - {{ pin_compatible('h5py') }}
- tqdm
- tabulate
diff --git a/requirements.txt b/requirements.txt
index 8eff46db1eacdeae2082181c185a43425a537d36..e394a12df53ee4280702ad258089f3704c007bd8 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,9 +1,8 @@
-bob.core
bob.extension
-bob.io.base
matplotlib
numpy
pandas
+h5py
pillow
setuptools
tabulate