def _augment(self, x, y):
for idx, (xx, yy) in enumerate(zip(x, y)):
if self.hflip and np.random.rand() > 0.5:
x[idx, ...] = kp.flip_axis(xx, axis=1)
y[idx, ...] = kp.flip_axis(yy, axis=1)
if self.vflip and np.random.rand() > 0.5:
x[idx, ...] = kp.flip_axis(xx, axis=0)
y[idx, ...] = kp.flip_axis(yy, axis=0)
if self.brg is not None:
# random_brightness per channel
for chn in range(xx.shape[-1]):
u = np.random.uniform(*self.brg)
x[idx, ..., chn:chn + 1] = kp.apply_brightness_shift(
xx[..., chn:chn + 1], u)
if self.rg > 0 or self.wrg > 0 or self.hrg > 0 or self.zrg is not None:
params = {
'theta': 0,
'tx': 0,
'ty': 0,
'shear': 0,
'zx': 1,
'zy': 1
}
if self.rg > 0:
params['theta'] = np.random.uniform(-self.rg, self.rg)
if self.wrg > 0 or self.hrg > 0:
h, w = xx.shape[0], xx.shape[1]
params['tx'] = np.random.uniform(-self.wrg, self.wrg) * w
params['ty'] = np.random.uniform(-self.hrg, self.hrg) * h
if self.zrg is not None:
params['zx'] = np.random.uniform(*self.zrg, 1)[0]
params['zy'] = params['zx']
x[idx, ...] = kp.apply_affine_transform(xx, **params)
y[idx, ...] = kp.apply_affine_transform(yy, **params)
return x, y
def random_global_brightness_shift(seq, brightness_range):
"""
perturb sequence wide brightness -- the brightness of the entire sequence
"""
brightness_lo, brightness_hi = brightness_range
u = np.random.uniform(brightness_lo, brightness_hi)
return [apply_brightness_shift(x, u) for x in seq]
def apply_transform(self, x, transform_parameters):
"""Applies a transformation to an image according to given parameters.
# Arguments
x: 3D tensor, single image.
transform_parameters: Dictionary with string - parameter pairs
describing the transformation.
Currently, the following parameters
from the dictionary are used:
- `'theta'`: Float. Rotation angle in degrees.
- `'tx'`: Float. Shift in the x direction.
- `'ty'`: Float. Shift in the y direction.
- `'shear'`: Float. Shear angle in degrees.
- `'zx'`: Float. Zoom in the x direction.
- `'zy'`: Float. Zoom in the y direction.
- `'flip_horizontal'`: Boolean. Horizontal flip.
- `'flip_vertical'`: Boolean. Vertical flip.
- `'channel_shift_intencity'`: Float. Channel shift intensity.
- `'brightness'`: Float. Brightness shift intensity.
# Returns
A transformed version of the input (same shape).
"""
# x is a single image, so it doesn't have image number at index 0
img_row_axis = self.row_axis - 1
img_col_axis = self.col_axis - 1
img_channel_axis = self.channel_axis - 1
x = apply_affine_transform(x,
transform_parameters.get('theta', 0),
transform_parameters.get('tx', 0),
transform_parameters.get('ty', 0),
transform_parameters.get('shear', 0),
transform_parameters.get('zx', 1),
transform_parameters.get('zy', 1),
row_axis=img_row_axis,
col_axis=img_col_axis,
channel_axis=img_channel_axis,
fill_mode=self.fill_mode,
cval=self.cval,
order=self.interpolation_order)
if transform_parameters.get('channel_shift_intensity') is not None:
x = apply_channel_shift(
x, transform_parameters['channel_shift_intensity'],
img_channel_axis)
if transform_parameters.get('flip_horizontal', False):
x = flip_axis(x, img_col_axis)
if transform_parameters.get('flip_vertical', False):
x = flip_axis(x, img_row_axis)
if transform_parameters.get('brightness') is not None:
x = apply_brightness_shift(x, transform_parameters['brightness'])
return x
def random_brightness(image, label, brightness_range):
if np.ndim(label) == 2:
label = np.expand_dims(label, axis=-1)
assert np.ndim(label) == 3
if brightness_range is not None:
if isinstance(brightness_range, (tuple, list)) and len(brightness_range) == 2:
brightness = np.random.uniform(brightness_range[0], brightness_range[1])
else:
raise ValueError('`brightness_range` should be '
'a tuple or list of two floats. '
'Received: %s' % (brightness_range,))
image = keras_image.apply_brightness_shift(image, brightness)
return image, label
def random_brightness(image, label, brightness_range):
if np.ndim(label) == 2:
label = np.expand_dims(label, axis=-1)
assert np.ndim(label) == 3
if np.ndim(image) == 2:
#need color image to triple grayscale
image = np.stack((image, ) * 3, axis=2).astype('uint8')
if brightness_range is not None:
if isinstance(brightness_range,
(tuple, list)) and len(brightness_range) == 2:
brightness = np.random.uniform(brightness_range[0],
brightness_range[1])
else:
raise ValueError('`brightness_range` should be '
'a tuple or list of two floats. '
'Received: %s' % (brightness_range, ))
image = keras_image.apply_brightness_shift(Image.fromarray(image),
brightness)
image = image[:, :, 0]
return image, label
def _apply_brightness(self,image,brightness):
return np.stack([IM.apply_brightness_shift(np.expand_dims(image[i],axis=2),brightness) for i in range(image.shape[0])],axis=0)
def keras(self, img):
return keras.apply_brightness_shift(img,
brightness=1.5).astype(np.uint8)
def keras(self, img):
return keras.apply_brightness_shift(img, brightness=1.5).astype(np.uint8)
