API - Preprocessing

We provide abundant data augmentation and processing functions by using Numpy, Scipy, Threading and Queue. However, we recommend you to use TensorFlow operation function like tf.image.central_crop, more TensorFlow data augmentation method can be found here and tutorial_cifar10_tfrecord.py. Some of the code in this package are borrowed from Keras.

threading_data([data, fn, thread_count]) Return a batch of result by given data.
rotation(x[, rg, is_random, row_index, ...]) Rotate an image randomly or non-randomly.
rotation_multi(x[, rg, is_random, ...]) Rotate multiple images with the same arguments, randomly or non-randomly.
crop(x, wrg, hrg[, is_random, row_index, ...]) Randomly or centrally crop an image.
crop_multi(x, wrg, hrg[, is_random, ...]) Randomly or centrally crop multiple images.
flip_axis(x, axis[, is_random]) Flip the axis of an image, such as flip left and right, up and down, randomly or non-randomly,
flip_axis_multi(x, axis[, is_random]) Flip the axises of multiple images together, such as flip left and right, up and down, randomly or non-randomly,
shift(x[, wrg, hrg, is_random, row_index, ...]) Shift an image randomly or non-randomly.
shift_multi(x[, wrg, hrg, is_random, ...]) Shift images with the same arguments, randomly or non-randomly.
shear(x[, intensity, is_random, row_index, ...]) Shear an image randomly or non-randomly.
shear_multi(x[, intensity, is_random, ...]) Shear images with the same arguments, randomly or non-randomly.
swirl(x[, center, strength, radius, ...]) Swirl an image randomly or non-randomly, see scikit-image swirl API and example.
swirl_multi(x[, center, strength, radius, ...]) Swirl multiple images with the same arguments, randomly or non-randomly.
elastic_transform(x, alpha, sigma[, mode, ...]) Elastic deformation of images as described in [Simard2003] .
elastic_transform_multi(x, alpha, sigma[, ...]) Elastic deformation of images as described in [Simard2003].
zoom(x[, zoom_range, is_random, row_index, ...]) Zoom in and out of a single image, randomly or non-randomly.
zoom_multi(x[, zoom_range, is_random, ...]) Zoom in and out of images with the same arguments, randomly or non-randomly.
brightness(x[, gamma, gain, is_random]) Change the brightness of a single image, randomly or non-randomly.
brightness_multi(x[, gamma, gain, is_random]) Change the brightness of multiply images, randomly or non-randomly.
imresize(x[, size, interp, mode]) Resize an image by given output size and method.
samplewise_norm(x[, rescale, ...]) Normalize an image by rescale, samplewise centering and samplewise centering in order.
featurewise_norm(x[, mean, std, epsilon]) Normalize every pixels by the same given mean and std, which are usually compute from all examples.
channel_shift(x, intensity[, is_random, ...]) Shift the channels of an image, randomly or non-randomly, see numpy.rollaxis.
channel_shift_multi(x, intensity[, ...]) Shift the channels of images with the same arguments, randomly or non-randomly, see numpy.rollaxis .
drop(x[, keep]) Randomly set some pixels to zero by a given keeping probability.
transform_matrix_offset_center(matrix, x, y) Return transform matrix offset center.
apply_transform(x, transform_matrix[, ...]) Return transformed images by given transform_matrix from transform_matrix_offset_center.
projective_transform_by_points(x, src, dst) Projective transform by given coordinates, usually 4 coordinates.
array_to_img(x[, dim_ordering, scale]) Converts a numpy array to PIL image object (uint8 format).
find_contours(x[, level, fully_connected, ...]) Find iso-valued contours in a 2D array for a given level value, returns list of (n, 2)-ndarrays see skimage.measure.find_contours .
pt2map([list_points, size, val]) Inputs a list of points, return a 2D image.
binary_dilation(x[, radius]) Return fast binary morphological dilation of an image.
dilation(x[, radius]) Return greyscale morphological dilation of an image, see skimage.morphology.dilation.
binary_erosion(x[, radius]) Return binary morphological erosion of an image, see skimage.morphology.binary_erosion.
erosion(x[, radius]) Return greyscale morphological erosion of an image, see skimage.morphology.erosion.
pad_sequences(sequences[, maxlen, dtype, ...]) Pads each sequence to the same length: the length of the longest sequence.
remove_pad_sequences(sequences[, pad_id]) Remove padding.
process_sequences(sequences[, end_id, ...]) Set all tokens(ids) after END token to the padding value, and then shorten (option) it to the maximum sequence length in this batch.
sequences_add_start_id(sequences[, ...]) Add special start token(id) in the beginning of each sequence.
sequences_add_end_id(sequences[, end_id]) Add special end token(id) in the end of each sequence.
sequences_add_end_id_after_pad(sequences[, ...]) Add special end token(id) in the end of each sequence.
sequences_get_mask(sequences[, pad_val]) Return mask for sequences.
distorted_images([images, height, width]) Distort images for generating more training data.
crop_central_whiten_images([images, height, ...]) Crop the central of image, and normailize it for test data.

Threading

tensorlayer.prepro.threading_data(data=None, fn=None, thread_count=None, **kwargs)[source]

Return a batch of result by given data. Usually be used for data augmentation.

Parameters:

data : numpy array, file names and etc, see Examples below.

thread_count : the number of threads to use

fn : the function for data processing.

more args : the args for fn, see Examples below.

References

Examples

  • Single array
>>> X --> [batch_size, row, col, 1] greyscale
>>> results = threading_data(X, zoom, zoom_range=[0.5, 1], is_random=True)
... results --> [batch_size, row, col, channel]
>>> tl.visualize.images2d(images=np.asarray(results), second=0.01, saveable=True, name='after', dtype=None)
>>> tl.visualize.images2d(images=np.asarray(X), second=0.01, saveable=True, name='before', dtype=None)
  • List of array (e.g. functions with multi)
>>> X, Y --> [batch_size, row, col, 1]  greyscale
>>> data = threading_data([_ for _ in zip(X, Y)], zoom_multi, zoom_range=[0.5, 1], is_random=True)
... data --> [batch_size, 2, row, col, 1]
>>> X_, Y_ = data.transpose((1,0,2,3,4))
... X_, Y_ --> [batch_size, row, col, 1]
>>> tl.visualize.images2d(images=np.asarray(X_), second=0.01, saveable=True, name='after', dtype=None)
>>> tl.visualize.images2d(images=np.asarray(Y_), second=0.01, saveable=True, name='before', dtype=None)
  • Single array split across thread_count threads (e.g. functions with multi)
>>> X, Y --> [batch_size, row, col, 1]  greyscale
>>> data = threading_data(X, zoom_multi, 8, zoom_range=[0.5, 1], is_random=True)
... data --> [batch_size, 2, row, col, 1]
>>> X_, Y_ = data.transpose((1,0,2,3,4))
... X_, Y_ --> [batch_size, row, col, 1]
>>> tl.visualize.images2d(images=np.asarray(X_), second=0.01, saveable=True, name='after', dtype=None)
>>> tl.visualize.images2d(images=np.asarray(Y_), second=0.01, saveable=True, name='before', dtype=None)
  • Customized function for image segmentation
>>> def distort_img(data):
...     x, y = data
...     x, y = flip_axis_multi([x, y], axis=0, is_random=True)
...     x, y = flip_axis_multi([x, y], axis=1, is_random=True)
...     x, y = crop_multi([x, y], 100, 100, is_random=True)
...     return x, y
>>> X, Y --> [batch_size, row, col, channel]
>>> data = threading_data([_ for _ in zip(X, Y)], distort_img)
>>> X_, Y_ = data.transpose((1,0,2,3,4))

Images

  • These functions only apply on a single image, use threading_data to apply multiple threading see tutorial_image_preprocess.py.
  • All functions have argument is_random.
  • All functions end with multi , usually be used for image segmentation i.e. the input and output image should be matched.

Rotation

tensorlayer.prepro.rotation(x, rg=20, is_random=False, row_index=0, col_index=1, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Rotate an image randomly or non-randomly.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

rg : int or float

Degree to rotate, usually 0 ~ 180.

is_random : boolean, default False

If True, randomly rotate.

row_index, col_index, channel_index : int

Index of row, col and channel, default (0, 1, 2), for theano (1, 2, 0).

fill_mode : string

Method to fill missing pixel, default ‘nearest’, more options ‘constant’, ‘reflect’ or ‘wrap’

cval : scalar, optional

Value used for points outside the boundaries of the input if mode=’constant’. Default is 0.0

order : int, optional

The order of interpolation. The order has to be in the range 0-5. See apply_transform.

Examples

>>> x --> [row, col, 1] greyscale
>>> x = rotation(x, rg=40, is_random=False)
>>> tl.visualize.frame(x[:,:,0], second=0.01, saveable=True, name='temp',cmap='gray')
tensorlayer.prepro.rotation_multi(x, rg=20, is_random=False, row_index=0, col_index=1, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Rotate multiple images with the same arguments, randomly or non-randomly. Usually be used for image segmentation which x=[X, Y], X and Y should be matched.

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see rotation.

Examples

>>> x, y --> [row, col, 1]  greyscale
>>> x, y = rotation_multi([x, y], rg=90, is_random=False)
>>> tl.visualize.frame(x[:,:,0], second=0.01, saveable=True, name='x',cmap='gray')
>>> tl.visualize.frame(y[:,:,0], second=0.01, saveable=True, name='y',cmap='gray')

Crop

tensorlayer.prepro.crop(x, wrg, hrg, is_random=False, row_index=0, col_index=1, channel_index=2)[source]

Randomly or centrally crop an image.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

wrg : float

Size of weight.

hrg : float

Size of height.

is_random : boolean, default False

If True, randomly crop, else central crop.

row_index, col_index, channel_index : int

Index of row, col and channel, default (0, 1, 2), for theano (1, 2, 0).

tensorlayer.prepro.crop_multi(x, wrg, hrg, is_random=False, row_index=0, col_index=1, channel_index=2)[source]

Randomly or centrally crop multiple images.

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see crop.

Flip

tensorlayer.prepro.flip_axis(x, axis, is_random=False)[source]

Flip the axis of an image, such as flip left and right, up and down, randomly or non-randomly,

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

axis : int

  • 0, flip up and down
  • 1, flip left and right
  • 2, flip channel

is_random : boolean, default False

If True, randomly flip.

tensorlayer.prepro.flip_axis_multi(x, axis, is_random=False)[source]

Flip the axises of multiple images together, such as flip left and right, up and down, randomly or non-randomly,

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see flip_axis.

Shift

tensorlayer.prepro.shift(x, wrg=0.1, hrg=0.1, is_random=False, row_index=0, col_index=1, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Shift an image randomly or non-randomly.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

wrg : float

Percentage of shift in axis x, usually -0.25 ~ 0.25.

hrg : float

Percentage of shift in axis y, usually -0.25 ~ 0.25.

is_random : boolean, default False

If True, randomly shift.

row_index, col_index, channel_index : int

Index of row, col and channel, default (0, 1, 2), for theano (1, 2, 0).

fill_mode : string

Method to fill missing pixel, default ‘nearest’, more options ‘constant’, ‘reflect’ or ‘wrap’.

cval : scalar, optional

Value used for points outside the boundaries of the input if mode=’constant’. Default is 0.0.

order : int, optional

The order of interpolation. The order has to be in the range 0-5. See apply_transform.

tensorlayer.prepro.shift_multi(x, wrg=0.1, hrg=0.1, is_random=False, row_index=0, col_index=1, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Shift images with the same arguments, randomly or non-randomly. Usually be used for image segmentation which x=[X, Y], X and Y should be matched.

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see shift.

Shear

tensorlayer.prepro.shear(x, intensity=0.1, is_random=False, row_index=0, col_index=1, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Shear an image randomly or non-randomly.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

intensity : float

Percentage of shear, usually -0.5 ~ 0.5 (is_random==True), 0 ~ 0.5 (is_random==False), you can have a quick try by shear(X, 1).

is_random : boolean, default False

If True, randomly shear.

row_index, col_index, channel_index : int

Index of row, col and channel, default (0, 1, 2), for theano (1, 2, 0).

fill_mode : string

Method to fill missing pixel, default ‘nearest’, more options ‘constant’, ‘reflect’ or ‘wrap’.

cval : scalar, optional

Value used for points outside the boundaries of the input if mode=’constant’. Default is 0.0.

order : int, optional

The order of interpolation. The order has to be in the range 0-5. See apply_transform.

tensorlayer.prepro.shear_multi(x, intensity=0.1, is_random=False, row_index=0, col_index=1, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Shear images with the same arguments, randomly or non-randomly. Usually be used for image segmentation which x=[X, Y], X and Y should be matched.

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see shear.

Swirl

tensorlayer.prepro.swirl(x, center=None, strength=1, radius=100, rotation=0, output_shape=None, order=1, mode='constant', cval=0, clip=True, preserve_range=False, is_random=False)[source]

Swirl an image randomly or non-randomly, see scikit-image swirl API and example.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

center : (row, column) tuple or (2,) ndarray, optional

Center coordinate of transformation.

strength : float, optional

The amount of swirling applied.

radius : float, optional

The extent of the swirl in pixels. The effect dies out rapidly beyond radius.

rotation : float, (degree) optional

Additional rotation applied to the image, usually [0, 360], relates to center.

output_shape : tuple (rows, cols), optional

Shape of the output image generated. By default the shape of the input image is preserved.

order : int, optional

The order of the spline interpolation, default is 1. The order has to be in the range 0-5. See skimage.transform.warp for detail.

mode : {‘constant’, ‘edge’, ‘symmetric’, ‘reflect’, ‘wrap’}, optional

Points outside the boundaries of the input are filled according to the given mode, with ‘constant’ used as the default. Modes match the behaviour of numpy.pad.

cval : float, optional

Used in conjunction with mode ‘constant’, the value outside the image boundaries.

clip : bool, optional

Whether to clip the output to the range of values of the input image. This is enabled by default, since higher order interpolation may produce values outside the given input range.

preserve_range : bool, optional

Whether to keep the original range of values. Otherwise, the input image is converted according to the conventions of img_as_float.

is_random : boolean, default False

If True, random swirl.
  • random center = [(0 ~ x.shape[0]), (0 ~ x.shape[1])]
  • random strength = [0, strength]
  • random radius = [1e-10, radius]
  • random rotation = [-rotation, rotation]

Examples

>>> x --> [row, col, 1] greyscale
>>> x = swirl(x, strength=4, radius=100)
tensorlayer.prepro.swirl_multi(x, center=None, strength=1, radius=100, rotation=0, output_shape=None, order=1, mode='constant', cval=0, clip=True, preserve_range=False, is_random=False)[source]

Swirl multiple images with the same arguments, randomly or non-randomly. Usually be used for image segmentation which x=[X, Y], X and Y should be matched.

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see swirl.

Elastic transform

tensorlayer.prepro.elastic_transform(x, alpha, sigma, mode='constant', cval=0, is_random=False)[source]

Elastic deformation of images as described in [Simard2003] .

Parameters:

x : numpy array, a greyscale image.

alpha : scalar factor.

sigma : scalar or sequence of scalars, the smaller the sigma, the more transformation.

Standard deviation for Gaussian kernel. The standard deviations of the Gaussian filter are given for each axis as a sequence, or as a single number, in which case it is equal for all axes.

mode : default constant, see scipy.ndimage.filters.gaussian_filter.

cval : float, optional. Used in conjunction with mode ‘constant’, the value outside the image boundaries.

is_random : boolean, default False

References

Examples

>>> x = elastic_transform(x, alpha = x.shape[1] * 3, sigma = x.shape[1] * 0.07)
tensorlayer.prepro.elastic_transform_multi(x, alpha, sigma, mode='constant', cval=0, is_random=False)[source]

Elastic deformation of images as described in [Simard2003].

Parameters:

x : list of numpy array

others : see elastic_transform.

Zoom

tensorlayer.prepro.zoom(x, zoom_range=(0.9, 1.1), is_random=False, row_index=0, col_index=1, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Zoom in and out of a single image, randomly or non-randomly.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

zoom_range : list or tuple

  • If is_random=False, (h, w) are the fixed zoom factor for row and column axies, factor small than one is zoom in.
  • If is_random=True, (min zoom out, max zoom out) for x and y with different random zoom in/out factor.

e.g (0.5, 1) zoom in 1~2 times.

is_random : boolean, default False

If True, randomly zoom.

row_index, col_index, channel_index : int

Index of row, col and channel, default (0, 1, 2), for theano (1, 2, 0).

fill_mode : string

Method to fill missing pixel, default ‘nearest’, more options ‘constant’, ‘reflect’ or ‘wrap’.

cval : scalar, optional

Value used for points outside the boundaries of the input if mode=’constant’. Default is 0.0.

order : int, optional

The order of interpolation. The order has to be in the range 0-5. See apply_transform.

tensorlayer.prepro.zoom_multi(x, zoom_range=(0.9, 1.1), is_random=False, row_index=0, col_index=1, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Zoom in and out of images with the same arguments, randomly or non-randomly. Usually be used for image segmentation which x=[X, Y], X and Y should be matched.

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see zoom.

Brightness

tensorlayer.prepro.brightness(x, gamma=1, gain=1, is_random=False)[source]

Change the brightness of a single image, randomly or non-randomly.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

gamma : float, small than 1 means brighter.

Non negative real number. Default value is 1, smaller means brighter.

  • If is_random is True, gamma in a range of (1-gamma, 1+gamma).

gain : float

The constant multiplier. Default value is 1.

is_random : boolean, default False

  • If True, randomly change brightness.

References

tensorlayer.prepro.brightness_multi(x, gamma=1, gain=1, is_random=False)[source]

Change the brightness of multiply images, randomly or non-randomly. Usually be used for image segmentation which x=[X, Y], X and Y should be matched.

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see brightness.

Resize

tensorlayer.prepro.imresize(x, size=[100, 100], interp='bicubic', mode=None)[source]

Resize an image by given output size and method. Warning, this function will rescale the value to [0, 255].

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

size : int, float or tuple (h, w)

  • int, Percentage of current size.
  • float, Fraction of current size.
  • tuple, Size of the output image.

interp : str, optional

Interpolation to use for re-sizing (‘nearest’, ‘lanczos’, ‘bilinear’, ‘bicubic’ or ‘cubic’).

mode : str, optional

The PIL image mode (‘P’, ‘L’, etc.) to convert arr before resizing.

Returns:

imresize : ndarray

The resized array of image.

References

Normalization

tensorlayer.prepro.samplewise_norm(x, rescale=None, samplewise_center=False, samplewise_std_normalization=False, channel_index=2, epsilon=1e-07)[source]

Normalize an image by rescale, samplewise centering and samplewise centering in order.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

rescale : rescaling factor.

If None or 0, no rescaling is applied, otherwise we multiply the data by the value provided (before applying any other transformation)

samplewise_center : set each sample mean to 0.

samplewise_std_normalization : divide each input by its std.

epsilon : small position value for dividing standard deviation.

Notes

When samplewise_center and samplewise_std_normalization are True.

  • For greyscale image, every pixels are subtracted and divided by the mean and std of whole image.
  • For RGB image, every pixels are subtracted and divided by the mean and std of this pixel i.e. the mean and std of a pixel is 0 and 1.

Examples

>>> x = samplewise_norm(x, samplewise_center=True, samplewise_std_normalization=True)
>>> print(x.shape, np.mean(x), np.std(x))
... (160, 176, 1), 0.0, 1.0
tensorlayer.prepro.featurewise_norm(x, mean=None, std=None, epsilon=1e-07)[source]

Normalize every pixels by the same given mean and std, which are usually compute from all examples.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

mean : value for subtraction.

std : value for division.

epsilon : small position value for dividing standard deviation.

Channel shift

tensorlayer.prepro.channel_shift(x, intensity, is_random=False, channel_index=2)[source]

Shift the channels of an image, randomly or non-randomly, see numpy.rollaxis.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

intensity : float

Intensity of shifting.

is_random : boolean, default False

If True, randomly shift.

channel_index : int

Index of channel, default 2.

tensorlayer.prepro.channel_shift_multi(x, intensity, is_random=False, channel_index=2)[source]

Shift the channels of images with the same arguments, randomly or non-randomly, see numpy.rollaxis . Usually be used for image segmentation which x=[X, Y], X and Y should be matched.

Parameters:

x : list of numpy array

List of images with dimension of [n_images, row, col, channel] (default).

others : see channel_shift.

Noise

tensorlayer.prepro.drop(x, keep=0.5)[source]

Randomly set some pixels to zero by a given keeping probability.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] or [row, col].

keep : float (0, 1)

The keeping probability, the lower more values will be set to zero.

Manual transform

tensorlayer.prepro.transform_matrix_offset_center(matrix, x, y)[source]

Return transform matrix offset center.

Parameters:

matrix : numpy array

Transform matrix

x, y : int

Size of image.

Examples

  • See rotation, shear, zoom.
tensorlayer.prepro.apply_transform(x, transform_matrix, channel_index=2, fill_mode='nearest', cval=0.0, order=1)[source]

Return transformed images by given transform_matrix from transform_matrix_offset_center.

Parameters:

x : numpy array

Batch of images with dimension of 3, [batch_size, row, col, channel].

transform_matrix : numpy array

Transform matrix (offset center), can be generated by transform_matrix_offset_center

channel_index : int

Index of channel, default 2.

fill_mode : string

Method to fill missing pixel, default ‘nearest’, more options ‘constant’, ‘reflect’ or ‘wrap’

cval : scalar, optional

Value used for points outside the boundaries of the input if mode=’constant’. Default is 0.0

order : int, optional

The order of interpolation. The order has to be in the range 0-5:

Examples

  • See rotation, shift, shear, zoom.
tensorlayer.prepro.projective_transform_by_points(x, src, dst, map_args={}, output_shape=None, order=1, mode='constant', cval=0.0, clip=True, preserve_range=False)[source]

Projective transform by given coordinates, usually 4 coordinates. see scikit-image.

Parameters:

x : numpy array

An image with dimension of [row, col, channel] (default).

src : list or numpy

The original coordinates, usually 4 coordinates of (x, y).

dst : list or numpy

The coordinates after transformation, the number of coordinates is the same with src.

map_args : dict, optional

Keyword arguments passed to inverse_map.

output_shape : tuple (rows, cols), optional

Shape of the output image generated. By default the shape of the input image is preserved. Note that, even for multi-band images, only rows and columns need to be specified.

order : int, optional

The order of interpolation. The order has to be in the range 0-5:

  • 0 Nearest-neighbor
  • 1 Bi-linear (default)
  • 2 Bi-quadratic
  • 3 Bi-cubic
  • 4 Bi-quartic
  • 5 Bi-quintic

mode : {‘constant’, ‘edge’, ‘symmetric’, ‘reflect’, ‘wrap’}, optional

Points outside the boundaries of the input are filled according to the given mode. Modes match the behaviour of numpy.pad.

cval : float, optional

Used in conjunction with mode ‘constant’, the value outside the image boundaries.

clip : bool, optional

Whether to clip the output to the range of values of the input image. This is enabled by default, since higher order interpolation may produce values outside the given input range.

preserve_range : bool, optional

Whether to keep the original range of values. Otherwise, the input image is converted according to the conventions of img_as_float.

References

Examples

>>> Assume X is an image from CIFAR 10, i.e. shape == (32, 32, 3)
>>> src = [[0,0],[0,32],[32,0],[32,32]]
>>> dst = [[10,10],[0,32],[32,0],[32,32]]
>>> x = projective_transform_by_points(X, src, dst)

Numpy and PIL

tensorlayer.prepro.array_to_img(x, dim_ordering=(0, 1, 2), scale=True)[source]

Converts a numpy array to PIL image object (uint8 format).

Parameters:

x : numpy array

A image with dimension of 3 and channels of 1 or 3.

dim_ordering : list or tuple of 3 int

Index of row, col and channel, default (0, 1, 2), for theano (1, 2, 0).

scale : boolean, default is True

If True, converts image to [0, 255] from any range of value like [-1, 2].

References

Find contours

tensorlayer.prepro.find_contours(x, level=0.8, fully_connected='low', positive_orientation='low')[source]

Find iso-valued contours in a 2D array for a given level value, returns list of (n, 2)-ndarrays see skimage.measure.find_contours .

Parameters:

x : 2D ndarray of double. Input data in which to find contours.

level : float. Value along which to find contours in the array.

fully_connected : str, {‘low’, ‘high’}. Indicates whether array elements below the given level value are to be considered fully-connected (and hence elements above the value will only be face connected), or vice-versa. (See notes below for details.)

positive_orientation : either ‘low’ or ‘high’. Indicates whether the output contours will produce positively-oriented polygons around islands of low- or high-valued elements. If ‘low’ then contours will wind counter-clockwise around elements below the iso-value. Alternately, this means that low-valued elements are always on the left of the contour.

Points to Image

tensorlayer.prepro.pt2map(list_points=[], size=(100, 100), val=1)[source]

Inputs a list of points, return a 2D image.

Parameters:

list_points : list of [x, y].

size : tuple of (w, h) for output size.

val : float or int for the contour value.

Binary dilation

tensorlayer.prepro.binary_dilation(x, radius=3)[source]

Return fast binary morphological dilation of an image. see skimage.morphology.binary_dilation.

Parameters:

x : 2D array image.

radius : int for the radius of mask.

Greyscale dilation

tensorlayer.prepro.dilation(x, radius=3)[source]

Return greyscale morphological dilation of an image, see skimage.morphology.dilation.

Parameters:

x : 2D array image.

radius : int for the radius of mask.

Binary erosion

tensorlayer.prepro.binary_erosion(x, radius=3)[source]

Return binary morphological erosion of an image, see skimage.morphology.binary_erosion.

Parameters:

x : 2D array image.

radius : int for the radius of mask.

Greyscale erosion

tensorlayer.prepro.erosion(x, radius=3)[source]

Return greyscale morphological erosion of an image, see skimage.morphology.erosion.

Parameters:

x : 2D array image.

radius : int for the radius of mask.

Sequence

More related functions can be found in tensorlayer.nlp.

Padding

tensorlayer.prepro.pad_sequences(sequences, maxlen=None, dtype='int32', padding='post', truncating='pre', value=0.0)[source]

Pads each sequence to the same length: the length of the longest sequence. If maxlen is provided, any sequence longer than maxlen is truncated to maxlen. Truncation happens off either the beginning (default) or the end of the sequence. Supports post-padding and pre-padding (default).

Parameters:

sequences : list of lists where each element is a sequence

maxlen : int, maximum length

dtype : type to cast the resulting sequence.

padding : ‘pre’ or ‘post’, pad either before or after each sequence.

truncating : ‘pre’ or ‘post’, remove values from sequences larger than

maxlen either in the beginning or in the end of the sequence

value : float, value to pad the sequences to the desired value.

Returns:

x : numpy array with dimensions (number_of_sequences, maxlen)

Examples

>>> sequences = [[1,1,1,1,1],[2,2,2],[3,3]]
>>> sequences = pad_sequences(sequences, maxlen=None, dtype='int32',
...                  padding='post', truncating='pre', value=0.)
... [[1 1 1 1 1]
...  [2 2 2 0 0]
...  [3 3 0 0 0]]

Remove Padding

tensorlayer.prepro.remove_pad_sequences(sequences, pad_id=0)[source]

Remove padding.

Parameters:

sequences : list of list.

pad_id : int.

Examples

>>> sequences = [[2,3,4,0,0], [5,1,2,3,4,0,0,0], [4,5,0,2,4,0,0,0]]
>>> print(remove_pad_sequences(sequences, pad_id=0))
... [[2, 3, 4], [5, 1, 2, 3, 4], [4, 5, 0, 2, 4]]

Process

tensorlayer.prepro.process_sequences(sequences, end_id=0, pad_val=0, is_shorten=True, remain_end_id=False)[source]

Set all tokens(ids) after END token to the padding value, and then shorten (option) it to the maximum sequence length in this batch.

Parameters:

sequences : numpy array or list of list with token IDs.

e.g. [[4,3,5,3,2,2,2,2], [5,3,9,4,9,2,2,3]]

end_id : int, the special token for END.

pad_val : int, replace the end_id and the ids after end_id to this value.

is_shorten : boolean, default True.

Shorten the sequences.

remain_end_id : boolean, default False.

Keep an end_id in the end.

Examples

>>> sentences_ids = [[4, 3, 5, 3, 2, 2, 2, 2],  <-- end_id is 2
...                  [5, 3, 9, 4, 9, 2, 2, 3]]  <-- end_id is 2
>>> sentences_ids = precess_sequences(sentences_ids, end_id=vocab.end_id, pad_val=0, is_shorten=True)
... [[4, 3, 5, 3, 0], [5, 3, 9, 4, 9]]

Add Start ID

tensorlayer.prepro.sequences_add_start_id(sequences, start_id=0, remove_last=False)[source]

Add special start token(id) in the beginning of each sequence.

Examples

>>> sentences_ids = [[4,3,5,3,2,2,2,2], [5,3,9,4,9,2,2,3]]
>>> sentences_ids = sequences_add_start_id(sentences_ids, start_id=2)
... [[2, 4, 3, 5, 3, 2, 2, 2, 2], [2, 5, 3, 9, 4, 9, 2, 2, 3]]
>>> sentences_ids = sequences_add_start_id(sentences_ids, start_id=2, remove_last=True)
... [[2, 4, 3, 5, 3, 2, 2, 2], [2, 5, 3, 9, 4, 9, 2, 2]]
  • For Seq2seq
>>> input = [a, b, c]
>>> target = [x, y, z]
>>> decode_seq = [start_id, a, b] <-- sequences_add_start_id(input, start_id, True)

Add End ID

tensorlayer.prepro.sequences_add_end_id(sequences, end_id=888)[source]

Add special end token(id) in the end of each sequence.

Parameters:

sequences : list of list.

end_id : int.

Examples

>>> sequences = [[1,2,3],[4,5,6,7]]
>>> print(sequences_add_end_id(sequences, end_id=999))
... [[1, 2, 3, 999], [4, 5, 6, 999]]

Add End ID after pad

tensorlayer.prepro.sequences_add_end_id_after_pad(sequences, end_id=888, pad_id=0)[source]

Add special end token(id) in the end of each sequence.

Parameters:

sequences : list of list.

end_id : int.

pad_id : int.

Examples

>>> sequences = [[1,2,0,0], [1,2,3,0], [1,2,3,4]]
>>> print(sequences_add_end_id_after_pad(sequences, end_id=99, pad_id=0))
... [[1, 2, 99, 0], [1, 2, 3, 99], [1, 2, 3, 4]]

Get Mask

tensorlayer.prepro.sequences_get_mask(sequences, pad_val=0)[source]

Return mask for sequences.

Examples

>>> sentences_ids = [[4, 0, 5, 3, 0, 0],
...                  [5, 3, 9, 4, 9, 0]]
>>> mask = sequences_get_mask(sentences_ids, pad_val=0)
... [[1 1 1 1 0 0]
...  [1 1 1 1 1 0]]

Tensor Opt

Note

These functions will be deprecated, see tutorial_cifar10_tfrecord.py for new information.

tensorlayer.prepro.distorted_images(images=None, height=24, width=24)[source]

Distort images for generating more training data.

Parameters:

images : 4D Tensor

The tensor or placeholder of images

height : int

The height for random crop.

width : int

The width for random crop.

Returns:

result : tuple of Tensor

(Tensor for distorted images, Tensor for while loop index)

Notes

  • The first image in ‘distorted_images’ should be removed.

References

Examples

>>> X_train, y_train, X_test, y_test = tl.files.load_cifar10_dataset(shape=(-1, 32, 32, 3), plotable=False)
>>> sess = tf.InteractiveSession()
>>> batch_size = 128
>>> x = tf.placeholder(tf.float32, shape=[batch_size, 32, 32, 3])
>>> distorted_images_op = tl.preprocess.distorted_images(images=x, height=24, width=24)
>>> sess.run(tf.initialize_all_variables())
>>> feed_dict={x: X_train[0:batch_size,:,:,:]}
>>> distorted_images, idx = sess.run(distorted_images_op, feed_dict=feed_dict)
>>> tl.visualize.images2d(X_train[0:9,:,:,:], second=2, saveable=False, name='cifar10', dtype=np.uint8, fig_idx=20212)
>>> tl.visualize.images2d(distorted_images[1:10,:,:,:], second=10, saveable=False, name='distorted_images', dtype=None, fig_idx=23012)
tensorlayer.prepro.crop_central_whiten_images(images=None, height=24, width=24)[source]

Crop the central of image, and normailize it for test data.

They are cropped to central of height * width pixels.

Whiten (Normalize) the images.

Parameters:

images : 4D Tensor

The tensor or placeholder of images

height : int

The height for central crop.

width : int

The width for central crop.

Returns:

result : tuple Tensor

(Tensor for distorted images, Tensor for while loop index)

Notes

The first image in ‘central_images’ should be removed.

Examples

>>> X_train, y_train, X_test, y_test = tl.files.load_cifar10_dataset(shape=(-1, 32, 32, 3), plotable=False)
>>> sess = tf.InteractiveSession()
>>> batch_size = 128
>>> x = tf.placeholder(tf.float32, shape=[batch_size, 32, 32, 3])
>>> central_images_op = tl.preprocess.crop_central_whiten_images(images=x, height=24, width=24)
>>> sess.run(tf.initialize_all_variables())
>>> feed_dict={x: X_train[0:batch_size,:,:,:]}
>>> central_images, idx = sess.run(central_images_op, feed_dict=feed_dict)
>>> tl.visualize.images2d(X_train[0:9,:,:,:], second=2, saveable=False, name='cifar10', dtype=np.uint8, fig_idx=20212)
>>> tl.visualize.images2d(central_images[1:10,:,:,:], second=10, saveable=False, name='central_images', dtype=None, fig_idx=23012)