未验证 提交 bbf98a01 编写于 作者: Q qingqing01 提交者: GitHub

Refine the doc in detection_output API. (#8689)

* Refine the doc in detection_output API.

* Refine the doc.
上级 bb60e920
...@@ -54,11 +54,17 @@ def detection_output(loc, ...@@ -54,11 +54,17 @@ def detection_output(loc,
score_threshold=0.01, score_threshold=0.01,
nms_eta=1.0): nms_eta=1.0):
""" """
**Detection Output Layer** **Detection Output Layer for Single Shot Multibox Detector (SSD).**
This layer applies the NMS to the output of network and computes the This operation is to get the detection results by performing following
predict bounding box location. The output's shape of this layer could two steps:
be zero if there is no valid bounding box.
1. Decode input bounding box predictions according to the prior boxes.
2. Get the final detection results by applying multi-class non maximum
suppression (NMS).
Please note, this operation doesn't clip the final output bounding boxes
to the image window.
Args: Args:
loc(Variable): A 3-D Tensor with shape [N, M, 4] represents the loc(Variable): A 3-D Tensor with shape [N, M, 4] represents the
...@@ -91,7 +97,15 @@ def detection_output(loc, ...@@ -91,7 +97,15 @@ def detection_output(loc,
nms_eta(float): The parameter for adaptive NMS. nms_eta(float): The parameter for adaptive NMS.
Returns: Returns:
The detected bounding boxes which are a Tensor. Variable: The detection outputs is a LoDTensor with shape [No, 6].
Each row has six values: [label, confidence, xmin, ymin, xmax, ymax].
`No` is the total number of detections in this mini-batch. For each
instance, the offsets in first dimension are called LoD, the offset
number is N + 1, N is the batch size. The i-th image has
`LoD[i + 1] - LoD[i]` detected results, if it is 0, the i-th image
has no detected results. If all images have not detected results,
all the elements in LoD are 0, and output tensor only contains one
value, which is -1.
Examples: Examples:
.. code-block:: python .. code-block:: python
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册