Generate batches of image data with real-time data augmentation. The data will be looped over (in batches).
image_data_generator( featurewise_center = FALSE, samplewise_center = FALSE, featurewise_std_normalization = FALSE, samplewise_std_normalization = FALSE, zca_whitening = FALSE, zca_epsilon = 1e-06, rotation_range = 0, width_shift_range = 0, height_shift_range = 0, brightness_range = NULL, shear_range = 0, zoom_range = 0, channel_shift_range = 0, fill_mode = "nearest", cval = 0, horizontal_flip = FALSE, vertical_flip = FALSE, rescale = NULL, preprocessing_function = NULL, data_format = NULL, validation_split = 0 )
Set input mean to 0 over the dataset, feature-wise.
Boolean. Set each sample mean to 0.
Divide inputs by std of the dataset, feature-wise.
Divide each input by its std.
apply ZCA whitening.
Epsilon for ZCA whitening. Default is 1e-6.
degrees (0 to 180).
fraction of total width.
fraction of total height.
the range of brightness to apply
shear intensity (shear angle in radians).
amount of zoom. if scalar z, zoom will be randomly picked
in the range
shift range for each channels.
One of "constant", "nearest", "reflect" or "wrap". Points outside the boundaries of the input are filled according to the given mode:
value used for points outside the boundaries when fill_mode is 'constant'. Default is 0.
whether to randomly flip images horizontally.
whether to randomly flip images vertically.
rescaling factor. If NULL or 0, no rescaling is applied, otherwise we multiply the data by the value provided (before applying any other transformation).
function that will be implied on each input. The function will run before any other modification on it. The function should take one argument: one image (tensor with rank 3), and should output a tensor with the same shape.
'channels_first' or 'channels_last'. In 'channels_first'
mode, the channels dimension (the depth) is at index 1, in 'channels_last'
mode it is at index 3. It defaults to the
fraction of images reserved for validation (strictly between 0 and 1).