tfm.vision.box_ops.bbox_intersection_over_area
Stay organized with collections
Save and categorize content based on your preferences.
Calculates IoAs (intersection over area) between proposal and ground truth boxes.
tfm.vision.box_ops.bbox_intersection_over_area(
boxes, gt_boxes
)
Some boxes or gt_boxes may have been padded. The returned iou 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, M, 4]. This tensor might
have paddings with a negative value.
|
Returns |
|---|
ioa
|
a tensor with as a shape of [batch_size, N, M].
|
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_intersection_over_area\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#L744-L796) |\n\nCalculates IoAs (intersection over area) between proposal and ground truth boxes. \n\n tfm.vision.box_ops.bbox_intersection_over_area(\n boxes, gt_boxes\n )\n\nSome `boxes` or `gt_boxes` may have been padded. The returned `iou` tensor\nfor these boxes will 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, M, 4\\]. This tensor might have paddings with a negative value. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|-------|---------------------------------------------------|\n| `ioa` | a tensor with as a shape of \\[batch_size, N, M\\]. |\n\n\u003cbr /\u003e"]]
View source on GitHub
