def __call__(self, results):
"""Call function.
Args:
results (dict): A dict containing the necessary information and
data for augmentation.
Returns:
dict: A dict containing the processed data and information.
"""
if self.file_client is None:
self.file_client = FileClient(self.io_backend, **self.kwargs)
filepaths = results[f'{self.key}_path']
if not isinstance(filepaths, list):
raise TypeError(
f'filepath should be list, but got {type(filepaths)}')
filepaths = [str(v) for v in filepaths]
imgs = []
shapes = []
if self.save_original_img:
ori_imgs = []
for filepath in filepaths:
img_bytes = self.file_client.get(filepath)
img = mmcv.imfrombytes(img_bytes,
flag=self.flag,
channel_order=self.channel_order) # HWC
# convert to y-channel, if specified
if self.convert_to is not None:
if self.channel_order == 'bgr' and self.convert_to.lower(
) == 'y':
img = mmcv.bgr2ycbcr(img, y_only=True)
elif self.channel_order == 'rgb':
img = mmcv.rgb2ycbcr(img, y_only=True)
else:
raise ValueError('Currently support only "bgr2ycbcr" or '
'"bgr2ycbcr".')
if img.ndim == 2:
img = np.expand_dims(img, axis=2)
imgs.append(img)
shapes.append(img.shape)
if self.save_original_img:
ori_imgs.append(img.copy())
results[self.key] = imgs
results[f'{self.key}_path'] = filepaths
results[f'{self.key}_ori_shape'] = shapes
if self.save_original_img:
results[f'ori_{self.key}'] = ori_imgs
return results
def to_y_channel(img):
"""Change to Y channel of YCbCr.
Args:
img (ndarray): Images with range [0, 255].
Returns:
(ndarray): Images with range [0, 255] (float type) without round.
"""
img = img.astype(np.float32) / 255.
if img.ndim == 3 and img.shape[2] == 3:
img = mmcv.rgb2ycbcr(img, y_only=True)
img = img[..., None]
return img * 255
def __call__(self, results):
"""Call function.
Args:
results (dict): A dict containing the necessary information and
data for augmentation.
Returns:
dict: A dict containing the processed data and information.
"""
filepath = str(results[f'{self.key}_path'])
if self.file_client is None:
self.file_client = FileClient(self.io_backend, **self.kwargs)
if self.use_cache:
if self.cache is None:
self.cache = dict()
if filepath in self.cache:
img = self.cache[filepath]
else:
img_bytes = self.file_client.get(filepath)
img = mmcv.imfrombytes(img_bytes,
flag=self.flag,
channel_order=self.channel_order,
backend=self.backend) # HWC
self.cache[filepath] = img
else:
img_bytes = self.file_client.get(filepath)
img = mmcv.imfrombytes(img_bytes,
flag=self.flag,
channel_order=self.channel_order,
backend=self.backend) # HWC
if self.convert_to is not None:
if self.channel_order == 'bgr' and self.convert_to.lower() == 'y':
img = mmcv.bgr2ycbcr(img, y_only=True)
elif self.channel_order == 'rgb':
img = mmcv.rgb2ycbcr(img, y_only=True)
else:
raise ValueError('Currently support only "bgr2ycbcr" or '
'"bgr2ycbcr".')
if img.ndim == 2:
img = np.expand_dims(img, axis=2)
results[self.key] = img
results[f'{self.key}_path'] = filepath
results[f'{self.key}_ori_shape'] = img.shape
if self.save_original_img:
results[f'ori_{self.key}'] = img.copy()
return results
def test_rgb2ycbcr():
with pytest.raises(TypeError):
# The img type should be np.float32 or np.uint8
in_img = np.random.rand(10, 10, 3).astype(np.uint64)
mmcv.rgb2ycbcr(in_img)
# float32
in_img = np.random.rand(10, 10, 3).astype(np.float32)
out_img = mmcv.rgb2ycbcr(in_img)
computed_ycbcr = np.empty_like(in_img)
for i in range(in_img.shape[0]):
for j in range(in_img.shape[1]):
r, g, b = in_img[i, j]
y = 16 + r * 65.481 + g * 128.553 + b * 24.966
cb = 128 - r * 37.797 - g * 74.203 + b * 112.0
cr = 128 + r * 112.0 - g * 93.786 - b * 18.214
computed_ycbcr[i, j, :] = [y, cb, cr]
computed_ycbcr /= 255.
assert_array_almost_equal(out_img, computed_ycbcr, decimal=2)
# y_only=True
out_img = mmcv.rgb2ycbcr(in_img, y_only=True)
computed_y = np.empty_like(out_img, dtype=out_img.dtype)
for i in range(in_img.shape[0]):
for j in range(in_img.shape[1]):
r, g, b = in_img[i, j]
y = 16 + r * 65.481 + g * 128.553 + b * 24.966
computed_y[i, j] = y
computed_y /= 255.
assert_array_almost_equal(out_img, computed_y, decimal=2)
# uint8
in_img = (np.random.rand(10, 10, 3) * 255).astype(np.uint8)
out_img = mmcv.rgb2ycbcr(in_img)
computed_ycbcr = np.empty_like(in_img)
in_img = in_img / 255.
for i in range(in_img.shape[0]):
for j in range(in_img.shape[1]):
r, g, b = in_img[i, j]
y = 16 + r * 65.481 + g * 128.553 + b * 24.966
cb = 128 - r * 37.797 - g * 74.203 + b * 112.0
cr = 128 + r * 112.0 - g * 93.786 - b * 18.214
y, cb, cr = y.round(), cb.round(), cr.round()
computed_ycbcr[i, j, :] = [y, cb, cr]
assert_image_almost_equal(out_img, computed_ycbcr)
# y_only=True
in_img = (np.random.rand(10, 10, 3) * 255).astype(np.uint8)
out_img = mmcv.rgb2ycbcr(in_img, y_only=True)
computed_y = np.empty_like(out_img, dtype=out_img.dtype)
in_img = in_img / 255.
for i in range(in_img.shape[0]):
for j in range(in_img.shape[1]):
r, g, b = in_img[i, j]
y = 16 + r * 65.481 + g * 128.553 + b * 24.966
y = y.round()
computed_y[i, j] = y
assert_image_almost_equal(out_img, computed_y)