LostTech.TensorFlow : API Documentation

Type image

Namespace tensorflow.compat.v2.image

Methods

Properties

Public static methods

Tensor crop_and_resize(object image, object boxes, object box_indices, object crop_size, string method, int extrapolation_value, string name)

object crop_and_resize_dyn(object image, object boxes, object box_indices, object crop_size, ImplicitContainer<T> method, ImplicitContainer<T> extrapolation_value, object name)

Tensor draw_bounding_boxes(IGraphNodeBase images, IGraphNodeBase boxes, IGraphNodeBase colors, string name)

object draw_bounding_boxes_dyn(object images, object boxes, object colors, object name)

Draw bounding boxes on a batch of images.

Outputs a copy of `images` but draws on top of the pixels zero or more bounding boxes specified by the locations in `boxes`. The coordinates of the each bounding box in `boxes` are encoded as `[y_min, x_min, y_max, x_max]`. The bounding box coordinates are floats in `[0.0, 1.0]` relative to the width and height of the underlying image.

For example, if an image is 100 x 200 pixels (height x width) and the bounding box is `[0.1, 0.2, 0.5, 0.9]`, the upper-left and bottom-right coordinates of the bounding box will be `(40, 10)` to `(180, 50)` (in (x,y) coordinates).

Parts of the bounding box may fall outside the image.
Parameters
object images
A `Tensor`. Must be one of the following types: `float32`, `half`. 4-D with shape `[batch, height, width, depth]`. A batch of images.
object boxes
A `Tensor` of type `float32`. 3-D with shape `[batch, num_bounding_boxes, 4]` containing bounding boxes.
object colors
object name
A name for the operation (optional).
Returns
object
A `Tensor`. Has the same type as `images`.

Tensor extract_glimpse(IGraphNodeBase input, IGraphNodeBase size, IGraphNodeBase offsets, bool centered, bool normalized, string noise, string name)

object extract_glimpse_dyn(object input, object size, object offsets, ImplicitContainer<T> centered, ImplicitContainer<T> normalized, ImplicitContainer<T> noise, object name)

Extracts a glimpse from the input tensor.

Returns a set of windows called glimpses extracted at location `offsets` from the input tensor. If the windows only partially overlaps the inputs, the non overlapping areas will be filled with random noise.

The result is a 4-D tensor of shape `[batch_size, glimpse_height, glimpse_width, channels]`. The channels and batch dimensions are the same as that of the input tensor. The height and width of the output windows are specified in the `size` parameter.

The argument `normalized` and `centered` controls how the windows are built:

* If the coordinates are normalized but not centered, 0.0 and 1.0 correspond to the minimum and maximum of each height and width dimension. * If the coordinates are both normalized and centered, they range from -1.0 to 1.0. The coordinates (-1.0, -1.0) correspond to the upper left corner, the lower right corner is located at (1.0, 1.0) and the center is at (0, 0). * If the coordinates are not normalized they are interpreted as numbers of pixels.
Parameters
object input
A `Tensor` of type `float32`. A 4-D float tensor of shape `[batch_size, height, width, channels]`.
object size
A `Tensor` of type `int32`. A 1-D tensor of 2 elements containing the size of the glimpses to extract. The glimpse height must be specified first, following by the glimpse width.
object offsets
A `Tensor` of type `float32`. A 2-D integer tensor of shape `[batch_size, 2]` containing the y, x locations of the center of each window.
ImplicitContainer<T> centered
An optional `bool`. Defaults to `True`. indicates if the offset coordinates are centered relative to the image, in which case the (0, 0) offset is relative to the center of the input images. If false, the (0,0) offset corresponds to the upper left corner of the input images.
ImplicitContainer<T> normalized
An optional `bool`. Defaults to `True`. indicates if the offset coordinates are normalized.
ImplicitContainer<T> noise
object name
A name for the operation (optional).
Returns
object
A `Tensor` of type `float32`.

Usage Example: ```python BATCH_SIZE = 1 IMAGE_HEIGHT = 3 IMAGE_WIDTH = 3 CHANNELS = 1 GLIMPSE_SIZE = (2, 2) image = tf.reshape(tf.range(9, delta=1, dtype=tf.float32), shape=(BATCH_SIZE, IMAGE_HEIGHT, IMAGE_WIDTH, CHANNELS)) output = tf.image.extract_glimpse(image, size=GLIMPSE_SIZE, offsets=[[1, 1]], centered=False, normalized=False) ```

object resize(IGraphNodeBase images, IEnumerable<int> size, ImplicitContainer<T> method, bool preserve_aspect_ratio, bool antialias, string name)

Resize `images` to `size` using the specified `method`.

Resized images will be distorted if their original aspect ratio is not the same as `size`. To avoid distortions see `tf.compat.v1.image.resize_image_with_pad`.

`method` can be one of:

* `ResizeMethod.BILINEAR`: [Bilinear interpolation.]( https://en.wikipedia.org/wiki/Bilinear_interpolation) * `ResizeMethod.NEAREST_NEIGHBOR`: [Nearest neighbor interpolation.]( https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation) * `ResizeMethod.BICUBIC`: [Bicubic interpolation.]( https://en.wikipedia.org/wiki/Bicubic_interpolation) * `ResizeMethod.AREA`: Area interpolation.

The return value has the same type as `images` if `method` is `ResizeMethod.NEAREST_NEIGHBOR`. It will also have the same type as `images` if the size of `images` can be statically determined to be the same as `size`, because `images` is returned in this case. Otherwise, the return value has type `float32`.
Parameters
IGraphNodeBase images
4-D Tensor of shape `[batch, height, width, channels]` or 3-D Tensor of shape `[height, width, channels]`.
IEnumerable<int> size
A 1-D int32 Tensor of 2 elements: `new_height, new_width`. The new size for the images.
ImplicitContainer<T> method
ResizeMethod. Defaults to `ResizeMethod.BILINEAR`.
bool preserve_aspect_ratio
Whether to preserve the aspect ratio. If this is set, then `images` will be resized to a size that fits in `size` while preserving the aspect ratio of the original image. Scales up the image if `size` is bigger than the current size of the `image`. Defaults to False.
bool antialias
string name
A name for this operation (optional).
Returns
object
If `images` was 4-D, a 4-D float Tensor of shape `[batch, new_height, new_width, channels]`. If `images` was 3-D, a 3-D float Tensor of shape `[new_height, new_width, channels]`.

object resize(IGraphNodeBase images, IGraphNodeBase size, ImplicitContainer<T> method, bool preserve_aspect_ratio, bool antialias, string name)

Resize `images` to `size` using the specified `method`.

Resized images will be distorted if their original aspect ratio is not the same as `size`. To avoid distortions see `tf.compat.v1.image.resize_image_with_pad`.

`method` can be one of:

* `ResizeMethod.BILINEAR`: [Bilinear interpolation.]( https://en.wikipedia.org/wiki/Bilinear_interpolation) * `ResizeMethod.NEAREST_NEIGHBOR`: [Nearest neighbor interpolation.]( https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation) * `ResizeMethod.BICUBIC`: [Bicubic interpolation.]( https://en.wikipedia.org/wiki/Bicubic_interpolation) * `ResizeMethod.AREA`: Area interpolation.

The return value has the same type as `images` if `method` is `ResizeMethod.NEAREST_NEIGHBOR`. It will also have the same type as `images` if the size of `images` can be statically determined to be the same as `size`, because `images` is returned in this case. Otherwise, the return value has type `float32`.
Parameters
IGraphNodeBase images
4-D Tensor of shape `[batch, height, width, channels]` or 3-D Tensor of shape `[height, width, channels]`.
IGraphNodeBase size
A 1-D int32 Tensor of 2 elements: `new_height, new_width`. The new size for the images.
ImplicitContainer<T> method
ResizeMethod. Defaults to `ResizeMethod.BILINEAR`.
bool preserve_aspect_ratio
Whether to preserve the aspect ratio. If this is set, then `images` will be resized to a size that fits in `size` while preserving the aspect ratio of the original image. Scales up the image if `size` is bigger than the current size of the `image`. Defaults to False.
bool antialias
string name
A name for this operation (optional).
Returns
object
If `images` was 4-D, a 4-D float Tensor of shape `[batch, new_height, new_width, channels]`. If `images` was 3-D, a 3-D float Tensor of shape `[new_height, new_width, channels]`.

object resize_dyn(object images, object size, ImplicitContainer<T> method, ImplicitContainer<T> preserve_aspect_ratio, ImplicitContainer<T> antialias, object name)

Resize `images` to `size` using the specified `method`.

Resized images will be distorted if their original aspect ratio is not the same as `size`. To avoid distortions see `tf.compat.v1.image.resize_image_with_pad`.

`method` can be one of:

* `ResizeMethod.BILINEAR`: [Bilinear interpolation.]( https://en.wikipedia.org/wiki/Bilinear_interpolation) * `ResizeMethod.NEAREST_NEIGHBOR`: [Nearest neighbor interpolation.]( https://en.wikipedia.org/wiki/Nearest-neighbor_interpolation) * `ResizeMethod.BICUBIC`: [Bicubic interpolation.]( https://en.wikipedia.org/wiki/Bicubic_interpolation) * `ResizeMethod.AREA`: Area interpolation.

The return value has the same type as `images` if `method` is `ResizeMethod.NEAREST_NEIGHBOR`. It will also have the same type as `images` if the size of `images` can be statically determined to be the same as `size`, because `images` is returned in this case. Otherwise, the return value has type `float32`.
Parameters
object images
4-D Tensor of shape `[batch, height, width, channels]` or 3-D Tensor of shape `[height, width, channels]`.
object size
A 1-D int32 Tensor of 2 elements: `new_height, new_width`. The new size for the images.
ImplicitContainer<T> method
ResizeMethod. Defaults to `ResizeMethod.BILINEAR`.
ImplicitContainer<T> preserve_aspect_ratio
Whether to preserve the aspect ratio. If this is set, then `images` will be resized to a size that fits in `size` while preserving the aspect ratio of the original image. Scales up the image if `size` is bigger than the current size of the `image`. Defaults to False.
ImplicitContainer<T> antialias
object name
A name for this operation (optional).
Returns
object
If `images` was 4-D, a 4-D float Tensor of shape `[batch, new_height, new_width, channels]`. If `images` was 3-D, a 3-D float Tensor of shape `[new_height, new_width, channels]`.

object sample_distorted_bounding_box(IGraphNodeBase image_size, IGraphNodeBase bounding_boxes, int seed, double min_object_covered, object aspect_ratio_range, object area_range, object max_attempts, object use_image_if_no_bounding_boxes, string name)

object sample_distorted_bounding_box_dyn(object image_size, object bounding_boxes, ImplicitContainer<T> seed, ImplicitContainer<T> min_object_covered, object aspect_ratio_range, object area_range, object max_attempts, object use_image_if_no_bounding_boxes, object name)

Public properties

PythonFunctionContainer crop_and_resize_fn_ get;

PythonFunctionContainer draw_bounding_boxes_fn_ get;

PythonFunctionContainer extract_glimpse_fn_ get;

PythonFunctionContainer resize_fn_ get;

PythonFunctionContainer sample_distorted_bounding_box_fn_ get;