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. Bounding boxes with score less than `score_threshold` are removed. 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 and more generally 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 the `tf.gather operation`. For example: selected_indices = tf.image.non_max_suppression_v2( boxes, scores, max_output_size, iou_threshold, score_threshold) selected_boxes = tf.gather(boxes, selected_indices) This op also supports a Soft-NMS (with Gaussian weighting) mode (c.f. Bodla et al, https://arxiv.org/abs/1704.04503) where boxes reduce the score of other overlapping boxes instead of directly causing them to be pruned. To enable this Soft-NMS mode, set the `soft_nms_sigma` parameter to be larger than 0.
Nested Classes
| class | NonMaxSuppression.Options | Optional attributes for NonMaxSuppression
|
|
Constants
| String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
| static <T extends TNumber> NonMaxSuppression<T> | |
| static NonMaxSuppression.Options |
padToMaxOutputSize(Boolean padToMaxOutputSize)
|
| Output<TInt32> |
selectedIndices()
A 1-D integer tensor of shape `[M]` representing the selected
indices from the boxes tensor, where `M <= max_output_size`.
|
| Output<T> |
selectedScores()
A 1-D float tensor of shape `[M]` representing the corresponding
scores for each selected box, where `M <= max_output_size`.
|
| Output<TInt32> |
validOutputs()
A 0-D integer tensor representing the number of valid elements in
`selected_indices`, with the valid elements appearing first.
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public static NonMaxSuppression<T> create (Scope scope, Operand<T> boxes, Operand<T> scores, Operand<TInt32> maxOutputSize, Operand<T> iouThreshold, Operand<T> scoreThreshold, Operand<T> softNmsSigma, Options... options)
Factory method to create a class wrapping a new NonMaxSuppression operation.
Parameters
| scope | current scope |
|---|---|
| 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). |
| maxOutputSize | A scalar integer tensor representing the maximum number of boxes to be selected by non max suppression. |
| iouThreshold | A 0-D float tensor representing the threshold for deciding whether boxes overlap too much with respect to IOU. |
| scoreThreshold | A 0-D float tensor representing the threshold for deciding when to remove boxes based on score. |
| softNmsSigma | A 0-D float tensor representing the sigma parameter for Soft NMS; see Bodla et al (c.f. https://arxiv.org/abs/1704.04503). When `soft_nms_sigma=0.0` (which is default), we fall back to standard (hard) NMS. |
| options | carries optional attributes values |
Returns
- a new instance of NonMaxSuppression
public static NonMaxSuppression.Options padToMaxOutputSize (Boolean padToMaxOutputSize)
Parameters
| padToMaxOutputSize | If true, the output `selected_indices` is padded to be of length `max_output_size`. Defaults to false. |
|---|
public Output<TInt32> selectedIndices ()
A 1-D integer tensor of shape `[M]` representing the selected indices from the boxes tensor, where `M <= max_output_size`.
public Output<T> selectedScores ()
A 1-D float tensor of shape `[M]` representing the corresponding scores for each selected box, where `M <= max_output_size`. Scores only differ from corresponding input scores when using Soft NMS (i.e. when `soft_nms_sigma>0`)