tfm.vision.box_ops.bbox_generalized_overlap
Stay organized with collections
Save and categorize content based on your preferences.
Calculates the GIOU between proposal and ground truth boxes.
tfm.vision.box_ops.bbox_generalized_overlap(
boxes, gt_boxes
)
The generalized intersection of union is an adjustment of the traditional IOU
metric which provides continuous updates even for predictions with no overlap.
This metric is defined in https://giou.stanford.edu/GIoU.pdf Note, some
gt_boxes may have been padded. The returned giou tensor for these boxes
will be -1.
Args |
|---|
boxes
|
a Tensor with a shape of [batch_size, N, 4]. N is the number of
proposals before groundtruth assignment (e.g., rpn_post_nms_topn). The
last dimension is the pixel coordinates in [ymin, xmin, ymax, xmax] form.
|
gt_boxes
|
a Tensor with a shape of [batch_size, max_num_instances, 4].
This tensor may have paddings with a negative value and will also be in
the [ymin, xmin, ymax, xmax] format.
|
Returns |
|---|
giou
|
a Tensor with as a shape of [batch_size, N, max_num_instances].
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-02-02 UTC.
[null,null,["Last updated 2024-02-02 UTC."],[],[],null,["# tfm.vision.box_ops.bbox_generalized_overlap\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/models/blob/v2.15.0/official/vision/ops/box_ops.py#L674-L741) |\n\nCalculates the GIOU between proposal and ground truth boxes. \n\n tfm.vision.box_ops.bbox_generalized_overlap(\n boxes, gt_boxes\n )\n\nThe generalized intersection of union is an adjustment of the traditional IOU\nmetric which provides continuous updates even for predictions with no overlap.\nThis metric is defined in \u003chttps://giou.stanford.edu/GIoU.pdf\u003e Note, some\n`gt_boxes` may have been padded. The returned `giou` tensor for these boxes\nwill be -1.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `boxes` | a `Tensor` with a shape of \\[batch_size, N, 4\\]. N is the number of proposals before groundtruth assignment (e.g., rpn_post_nms_topn). The last dimension is the pixel coordinates in \\[ymin, xmin, ymax, xmax\\] form. |\n| `gt_boxes` | a `Tensor` with a shape of \\[batch_size, max_num_instances, 4\\]. This tensor may have paddings with a negative value and will also be in the \\[ymin, xmin, ymax, xmax\\] format. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|--------|---------------------------------------------------------------------|\n| `giou` | a `Tensor` with as a shape of \\[batch_size, N, max_num_instances\\]. |\n\n\u003cbr /\u003e"]]
View source on GitHub