Skip to content

[Backport r0.11] Beautifier image doc #2119

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 27, 2020
Merged

[Backport r0.11] Beautifier image doc #2119

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions tensorflow_addons/image/color_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,11 +86,11 @@ def equalize(

Args:
images: A tensor of shape
(num_images, num_rows, num_columns, num_channels) (NHWC), or
(num_images, num_channels, num_rows, num_columns) (NCHW), or
(num_rows, num_columns, num_channels) (HWC), or
(num_channels, num_rows, num_columns) (CHW), or
(num_rows, num_columns) (HW). The rank must be statically known (the
`(num_images, num_rows, num_columns, num_channels)` (NHWC), or
`(num_images, num_channels, num_rows, num_columns)` (NCHW), or
`(num_rows, num_columns, num_channels)` (HWC), or
`(num_channels, num_rows, num_columns)` (CHW), or
`(num_rows, num_columns)` (HW). The rank must be statically known (the
shape is not `TensorShape(None)`).
data_format: Either 'channels_first' or 'channels_last'
name: The name of the op.
Expand Down Expand Up @@ -149,8 +149,8 @@ def sharpness(image: TensorLike, factor: Number) -> tf.Tensor:

Args:
images: A tensor of shape
(num_images, num_rows, num_columns, num_channels) (NHWC), or
(num_rows, num_columns, num_channels) (HWC)
`(num_images, num_rows, num_columns, num_channels)` (NHWC), or
`(num_rows, num_columns, num_channels)` (HWC)
factor: A floating point value or Tensor above 0.0.
Returns:
Image(s) with the same type and shape as `images`, sharper.
Expand Down
36 changes: 19 additions & 17 deletions tensorflow_addons/image/compose_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,26 +20,28 @@


def blend(image1: TensorLike, image2: TensorLike, factor: Number) -> tf.Tensor:
"""Blend image1 and image2 using 'factor'.
"""Blend `image1` and `image2` using `factor`.

Factor can be above 0.0. A value of 0.0 means only image1 is used.
A value of 1.0 means only image2 is used. A value between 0.0 and
1.0 means we linearly interpolate the pixel values between the two
images. A value greater than 1.0 "extrapolates" the difference
between the two pixel values, and we clip the results to values
between 0 and 255.
Factor can be above 0.0. A value of 0.0 means only `image1` is used.
A value of 1.0 means only `image2` is used. A value between 0.0 and
1.0 means we linearly interpolate the pixel values between the two
images. A value greater than 1.0 "extrapolates" the difference
between the two pixel values, and we clip the results to values
between 0 and 255.

Args:
image1: An image Tensor of shape (num_rows, num_columns,
num_channels) (HWC), or (num_rows, num_columns) (HW),
or (num_channels, num_rows, num_columns).
image2: An image Tensor of shape (num_rows, num_columns,
num_channels) (HWC), or (num_rows, num_columns) (HW),
or (num_channels, num_rows, num_columns).
factor: A floating point value or Tensor of type tf.float32 above 0.0.
Args:
image1: An image Tensor of shape
`(num_rows, num_columns, num_channels)` (HWC), or
`(num_rows, num_columns)` (HW), or
`(num_channels, num_rows, num_columns)` (CHW).
image2: An image Tensor of shape
`(num_rows, num_columns, num_channels)` (HWC), or
`(num_rows, num_columns)` (HW), or
`(num_channels, num_rows, num_columns)`.
factor: A floating point value or Tensor of type `tf.float32` above 0.0.

Returns:
A blended image Tensor of tf.float32.
Returns:
A blended image Tensor of `tf.float32`.

"""
with tf.name_scope("blend"):
Expand Down
2 changes: 1 addition & 1 deletion tensorflow_addons/image/connected_components.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ def connected_components(
(which is the connectivity used here).

Args:
images: A 2D (H, W) or 3D (N, H, W) Tensor of image (integer,
images: A 2D (H, W) or 3D (N, H, W) `Tensor` of image (integer,
floating point and boolean types are supported).
name: The name of the op.

Expand Down
35 changes: 18 additions & 17 deletions tensorflow_addons/image/cutout_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,18 +54,18 @@ def random_cutout(
) -> tf.Tensor:
"""Apply cutout (https://arxiv.org/abs/1708.04552) to images.

This operation applies a (mask_height x mask_width) mask of zeros to
a random location within `img`. The pixel values filled in will be of the
value `replace`. The located where the mask will be applied is randomly
chosen uniformly over the whole images.
This operation applies a `(mask_height x mask_width)` mask of zeros to
a random location within `images`. The pixel values filled in will be of
the value `replace`. The located where the mask will be applied is
randomly chosen uniformly over the whole images.

Args:
images: A tensor of shape
(batch_size, height, width, channels)
(NHWC), (batch_size, channels, height, width)(NCHW).
`(batch_size, height, width, channels)`
(NHWC), `(batch_size, channels, height, width)` (NCHW).
mask_size: Specifies how big the zero mask that will be generated is that
is applied to the images. The mask will be of size
(mask_height x mask_width). Note: mask_size should be divisible by 2.
`(mask_height x mask_width)`. Note: mask_size should be divisible by 2.
constant_values: What pixel value to fill in the images in the area that has
the cutout mask applied to it.
seed: A Python integer. Used in combination with `tf.random.set_seed` to
Expand All @@ -76,9 +76,9 @@ def random_cutout(
`(batch_size, ..., channels)` while `channels_first` corresponds to
inputs with shape `(batch_size, channels, ...)`.
Returns:
An image Tensor.
An image `Tensor`.
Raises:
InvalidArgumentError: if mask_size can't be divisible by 2.
InvalidArgumentError: if `mask_size` can't be divisible by 2.
"""
if data_format == "channels_first":
warnings.warn(
Expand Down Expand Up @@ -112,18 +112,19 @@ def cutout(
) -> tf.Tensor:
"""Apply cutout (https://arxiv.org/abs/1708.04552) to images.

This operation applies a (mask_height x mask_width) mask of zeros to
a location within `img` specified by the offset. The pixel values filled in will be of the
value `replace`. The located where the mask will be applied is randomly
This operation applies a `(mask_height x mask_width)` mask of zeros to
a location within `images` specified by the offset.
The pixel values filled in will be of the value `replace`.
The located where the mask will be applied is randomly
chosen uniformly over the whole images.

Args:
images: A tensor of shape (batch_size, height, width, channels)
(NHWC), (batch_size, channels, height, width)(NCHW).
images: A tensor of shape `(batch_size, height, width, channels)`
(NHWC), `(batch_size, channels, height, width)` (NCHW).
mask_size: Specifies how big the zero mask that will be generated is that
is applied to the images. The mask will be of size
(mask_height x mask_width). Note: mask_size should be divisible by 2.
offset: A tuple of (height, width) or (batch_size, 2)
`(mask_height x mask_width)`. Note: mask_size should be divisible by 2.
offset: A tuple of `(height, width)` or `(batch_size, 2)`
constant_values: What pixel value to fill in the images in the area that has
the cutout mask applied to it.
data_format: A string, one of `channels_last` (default) or `channels_first`.
Expand All @@ -134,7 +135,7 @@ def cutout(
Returns:
An image Tensor.
Raises:
InvalidArgumentError: if mask_size can't be divisible by 2.
InvalidArgumentError: if `mask_size` can't be divisible by 2.
"""
if data_format == "channels_first":
warnings.warn(
Expand Down
8 changes: 4 additions & 4 deletions tensorflow_addons/image/dense_image_warp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@ def dense_image_warp(
`(b, j - flow[b, j, i, 0], i - flow[b, j, i, 1])`. For locations outside
of the image, we use the nearest pixel values at the image boundary.

PLEASE NOTE: The definition of the flow field above is different from that
NOTE: The definition of the flow field above is different from that
of optical flow. This function expects the negative forward flow from
output image to source image. Given two images `I_1` and `I_2` and the
optical flow `F_12` from `I_1` to `I_2`, the image `I_1` can be
Expand All @@ -221,15 +221,15 @@ def dense_image_warp(
flow: A 4-D float `Tensor` with shape `[batch, height, width, 2]`.
name: A name for the operation (optional).

Note that image and flow can be of type tf.half, tf.float32, or
tf.float64, and do not necessarily have to be the same type.
Note that image and flow can be of type `tf.half`, `tf.float32`, or
`tf.float64`, and do not necessarily have to be the same type.

Returns:
A 4-D float `Tensor` with shape`[batch, height, width, channels]`
and same type as input image.

Raises:
ValueError: if height < 2 or width < 2 or the inputs have the wrong
ValueError: if `height < 2` or `width < 2` or the inputs have the wrong
number of dimensions.
"""
with tf.name_scope(name or "dense_image_warp"):
Expand Down
7 changes: 4 additions & 3 deletions tensorflow_addons/image/distance_transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,9 +34,10 @@ def euclidean_dist_transform(
"""Applies euclidean distance transform(s) to the image(s).

Args:
images: A tensor of shape (num_images, num_rows, num_columns, 1) (NHWC),
or (num_rows, num_columns, 1) (HWC) or (num_rows, num_columns) (HW).
dtype: DType of the output tensor.
images: A tensor of shape `(num_images, num_rows, num_columns, 1)`
(NHWC), or `(num_rows, num_columns, 1)` (HWC) or
`(num_rows, num_columns)` (HW).
dtype: `tf.dtypes.DType` of the output tensor.
name: The name of the op.

Returns:
Expand Down
18 changes: 9 additions & 9 deletions tensorflow_addons/image/distort_image_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,20 +43,20 @@ def random_hsv_in_yiq(

Args:
image: RGB image or images. Size of the last dimension must be 3.
max_delta_hue: float. Maximum value for the random delta_hue. Passing 0
max_delta_hue: `float`. Maximum value for the random delta_hue. Passing 0
disables adjusting hue.
lower_saturation: float. Lower bound for the random scale_saturation.
upper_saturation: float. Upper bound for the random scale_saturation.
lower_value: float. Lower bound for the random scale_value.
upper_value: float. Upper bound for the random scale_value.
lower_saturation: `float`. Lower bound for the random scale_saturation.
upper_saturation: `float`. Upper bound for the random scale_saturation.
lower_value: `float`. Lower bound for the random scale_value.
upper_value: `float`. Upper bound for the random scale_value.
seed: An operation-specific seed. It will be used in conjunction
with the graph-level seed to determine the real seeds that will be
used in this operation. Please see the documentation of
set_random_seed for its interaction with the graph-level random seed.
name: A name for this operation (optional).

Returns:
3-D float tensor of shape `[height, width, channels]`.
3-D float `Tensor` of shape `[height, width, channels]`.

Raises:
ValueError: if `max_delta`, `lower_saturation`, `upper_saturation`,
Expand Down Expand Up @@ -122,9 +122,9 @@ def adjust_hsv_in_yiq(

Args:
image: RGB image or images. Size of the last dimension must be 3.
delta_hue: float, the hue rotation amount, in radians.
scale_saturation: float, factor to multiply the saturation by.
scale_value: float, factor to multiply the value by.
delta_hue: `float`, the hue rotation amount, in radians.
scale_saturation: `float`, factor to multiply the saturation by.
scale_value: `float`, factor to multiply the value by.
name: A name for this operation (optional).

Returns:
Expand Down
49 changes: 25 additions & 24 deletions tensorflow_addons/image/interpolate_spline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,14 +23,15 @@
def _cross_squared_distance_matrix(x: TensorLike, y: TensorLike) -> tf.Tensor:
"""Pairwise squared distance between two (batch) matrices' rows (2nd dim).

Computes the pairwise distances between rows of x and rows of y
Computes the pairwise distances between rows of x and rows of y.

Args:
x: [batch_size, n, d] float `Tensor`
y: [batch_size, m, d] float `Tensor`
x: `[batch_size, n, d]` float `Tensor`.
y: `[batch_size, m, d]` float `Tensor`.

Returns:
squared_dists: [batch_size, n, m] float `Tensor`, where
squared_dists[b,i,j] = ||x[b,i,:] - y[b,j,:]||^2
squared_dists: `[batch_size, n, m]` float `Tensor`, where
`squared_dists[b,i,j] = ||x[b,i,:] - y[b,j,:]||^2`.
"""
x_norm_squared = tf.reduce_sum(tf.square(x), 2)
y_norm_squared = tf.reduce_sum(tf.square(y), 2)
Expand All @@ -52,14 +53,14 @@ def _pairwise_squared_distance_matrix(x: TensorLike) -> tf.Tensor:
"""Pairwise squared distance among a (batch) matrix's rows (2nd dim).

This saves a bit of computation vs. using
_cross_squared_distance_matrix(x,x)
`_cross_squared_distance_matrix(x, x)`

Args:
x: `[batch_size, n, d]` float `Tensor`
x: `[batch_size, n, d]` float `Tensor`.

Returns:
squared_dists: `[batch_size, n, n]` float `Tensor`, where
squared_dists[b,i,j] = ||x[b,i,:] - x[b,j,:]||^2
`squared_dists[b,i,j] = ||x[b,i,:] - x[b,j,:]||^2`.
"""

x_x_transpose = tf.matmul(x, x, adjoint_b=True)
Expand All @@ -83,17 +84,17 @@ def _solve_interpolation(
order: int,
regularization_weight: FloatTensorLike,
) -> TensorLike:
"""Solve for interpolation coefficients.
r"""Solve for interpolation coefficients.

Computes the coefficients of the polyharmonic interpolant for the
'training' data defined by (train_points, train_values) using the kernel
phi.
'training' data defined by `(train_points, train_values)` using the kernel
$\phi$.

Args:
train_points: `[b, n, d]` interpolation centers
train_values: `[b, n, k]` function values
order: order of the interpolation
regularization_weight: weight to place on smoothness regularization term
train_points: `[b, n, d]` interpolation centers.
train_values: `[b, n, k]` function values.
order: order of the interpolation.
regularization_weight: weight to place on smoothness regularization term.

Returns:
w: `[b, n, k]` weights on each interpolation center
Expand Down Expand Up @@ -173,15 +174,15 @@ def _apply_interpolation(
interpolated function values at query_points.

Args:
query_points: `[b, m, d]` x values to evaluate the interpolation at
query_points: `[b, m, d]` x values to evaluate the interpolation at.
train_points: `[b, n, d]` x values that act as the interpolation centers
( the c variables in the wikipedia article)
w: `[b, n, k]` weights on each interpolation center
v: `[b, d, k]` weights on each input dimension
order: order of the interpolation
(the c variables in the wikipedia article).
w: `[b, n, k]` weights on each interpolation center.
v: `[b, d, k]` weights on each input dimension.
order: order of the interpolation.

Returns:
Polyharmonic interpolation evaluated at points defined in query_points.
Polyharmonic interpolation evaluated at points defined in `query_points`.
"""

# First, compute the contribution from the rbf term.
Expand All @@ -207,11 +208,11 @@ def _phi(r: FloatTensorLike, order: int) -> FloatTensorLike:
See https://en.wikipedia.org/wiki/Polyharmonic_spline for the definition.

Args:
r: input op
order: interpolation order
r: input op.
order: interpolation order.

Returns:
phi_k evaluated coordinate-wise on r, for k = r
`phi_k` evaluated coordinate-wise on `r`, for `k = r`.
"""

# using EPSILON prevents log(0), sqrt0), etc.
Expand Down
6 changes: 3 additions & 3 deletions tensorflow_addons/image/resampler_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,13 +33,13 @@ def resampler(
The resampler currently only supports bilinear interpolation of 2D data.

Args:
data: Tensor of shape `[batch_size, data_height, data_width,
data: `Tensor` of shape `[batch_size, data_height, data_width,
data_num_channels]` containing 2D data that will be resampled.
warp: Tensor of minimum rank 2 containing the coordinates at
which resampling will be performed. Since only bilinear
interpolation is currently supported, the last dimension of the
`warp` tensor must be 2, representing the (x, y) coordinate where
x is the index for width and y is the index for height.
`warp` tensor must be 2, representing the `(x, y)` coordinate where
`x` is the index for width and `y` is the index for height.
name: Optional name of the op.
Returns:
Tensor of resampled values from `data`. The output tensor shape
Expand Down
Loading