QuantizedResizeBilinear

tensorflow C++ API

tensorflow::ops::QuantizedResizeBilinear

Resize quantizedimagestosizeusing quantized bilinear interpolation.

Summary

Input

images and output images must be quantized types.

Arguments:

• scope: A Scope object
• images: 4-D with shape[batch, height, width, channels].
• size: = A 1-D int32 Tensor of 2 elements:new_height, new_width. The new size for the images.

Optional attributes (seeAttrs):

• align_corners: If true, rescale input by (new_height - 1) / (height - 1), which exactly aligns the 4 corners of images and resized images. If false, rescale by new_height / height. Treat similarly the width dimension.

Returns:

• Outputresized_images: 4-D with shape[batch, new_height, new_width, channels].
• Outputout_min
• Outputout_max

Constructor

• QuantizedResizeBilinear(const ::tensorflow::Scope& scope, ::tensorflow::Input images, ::tensorflow::Input size, ::tensorflow::Input min, ::tensorflow::Input max, const QuantizedResizeBilinear::Attrs& attrs).

Public attributes

• tensorflow::Output out_max.
• tensorflow::Output out_min.
• tensorflow::Output resized_images.

QuantizedResizeBilinear block

Source link : https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_image_ops.cpp

Argument:

• Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
• images : connect Input node.
• size: connect Input node or input int32 value.
• min: connect Input node or input float value.
• max: connect Input node or input float value.
• QuantizedResizeBilinear ::Attrs attrs : input attrs. ex) align_corners_ = false;

Return:

• Output resized_images: Output object of QuantizedResizeBilinear class object.
• Output max: Output object of QuantizedResizeBilinear class object.
• Output min: Output object of QuantizedResizeBilinear class object.

Result:

• std::vector(Tensor) product_result : Returned object of executed result by calling session.

Using Method

Quantize function is not yet supported in windows.