size using area interpolation.
Input images can be of different types but output images are always float.
Each output pixel is computed by first transforming the pixel's footprint into the input tensor and then averaging the pixels that intersect the footprint. An input pixel's contribution to the average is weighted by the fraction of its area that intersects the footprint. This is the same as OpenCV's INTER_AREA.
[batch, height, width, channels].
new_height, new_width. The new size for the images.
Optional attributes (see
Output: 4-D with shape
[batch, new_height, new_width, channels].
|Constructors and Destructors|
| || |
|Public static functions|
Optional attribute setters for ResizeArea.
ResizeArea( const ::tensorflow::Scope & scope, ::tensorflow::Input images, ::tensorflow::Input size )
ResizeArea( const ::tensorflow::Scope & scope, ::tensorflow::Input images, ::tensorflow::Input size, const ResizeArea::Attrs & attrs )
::tensorflow::Node * node() const
Attrs AlignCorners( bool x )
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.