ExtractGlimpse

tensorflow C++ API

tensorflow::ops::ExtractGlimpse

Greedily selects a subset of bounding boxes in descending order of score, pruning away boxes that have high intersection-over-union (IOU) overlap with previously selected boxes.

Summary

Bounding boxes are supplied as [y1, x1, y2, x2], where (y1, x1) and (y2, x2) are the coordinates of any diagonal pair of box corners and the coordinates can be provided as normalized (i.e., lying in the interval [0, 1]) or absolute. Note that this algorithm is agnostic to where the origin is in the coordinate system. Note that this algorithm is invariant to orthogonal transformations and translations of the coordinate system; thus translating or reflections of the coordinate system result in the same boxes being selected by the algorithm. The output of this operation is a set of integers indexing into the input collection of bounding boxes representing the selected boxes. The bounding box coordinates corresponding to the selected indices can then be obtained using thetf.gather operation. For example: selected_indices = tf.image.non_max_suppression( boxes, scores, max_output_size, iou_threshold) selected_boxes = tf.gather(boxes, selected_indices)

Arguments:

• scope: A Scope object
• boxes: A 2-D float tensor of shape[num_boxes, 4].
• scores: A 1-D float tensor of shape[num_boxes]representing a single score corresponding to each box (each row of boxes).
• max_output_size: A scalar integer tensor representing the maximum number of boxes to be selected by non max suppression.

Optional attributes (seeAttrs):

• iou_threshold: A float representing the threshold for deciding whether boxes overlap too much with respect to IOU.

Returns:

• Output: A 1-D integer tensor of shape[M]representing the selected indices from the boxes tensor, whereM <= max_output_size.

Constructor

• NonMaxSuppression(const ::tensorflow::Scope & scope, ::tensorflow::Input boxes, ::tensorflow::Input scores, ::tensorflow::Input max_output_size, const NonMaxSuppression::Attrs & attrs) .

Public attributes

• tensorflow::Output selected_indices.

NonMaxSuppression 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.)
• boxes: connect Input node.
• scores: connect Input node or input int32 value.
• max_output_size: connect Input node or input float value.
• NonMaxSuppression::Attrs attrs : input attrs. ex) iou_threshold_ = 0.5f;

Return:

• Output selected_indices: Output object of NonMaxSuppression class object.

Result:

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

Using Method