def random_channel_shift(image, label, channel_shift_range):
if np.ndim(label) == 2:
label = np.expand_dims(label, axis=-1)
assert np.ndim(label) == 3
if channel_shift_range > 0:
channel_shift_intensity = np.random.uniform(-channel_shift_range, channel_shift_range)
image = keras_image.apply_channel_shift(image, channel_shift_intensity, channel_axis=2)
return image, label
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_channel_shift(image, label, channel_shift_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 channel_shift_range > 0:
channel_shift_intensity = np.random.uniform(-channel_shift_range,
channel_shift_range)
image = keras_image.apply_channel_shift(image,
channel_shift_intensity,
channel_axis=2)
image = image[:, :, 0]
return image, label
def keras(self, img):
img = keras.apply_channel_shift(img, intensity=100, channel_axis=2)
return np.ascontiguousarray(img)
def keras(self, img):
return keras.apply_channel_shift(img, intensity=100, channel_axis=2)
def keras(self, img):
return keras.apply_channel_shift(img, intensity=100, channel_axis=2)
