提交 466a10dc 编写于 作者: J jerrywgz

refine code, test=develop

上级 9eb2d7b3
......@@ -520,7 +520,7 @@ independently for each class. The outputs is a 2-D LoDTenosr, for each
image, the offsets in first dimension of LoDTensor are called LoD, the number
of offset is N + 1, where N is the batch size. If LoD[i + 1] - LoD[i] == 0,
means there is no detected bbox for this image. If there is no detected boxes
for all images, all the elements in LoD are set to {0,1}, and the Out only
for all images, all the elements in LoD are set to {1}, and the Out only
contains one value which is -1.
)DOC");
}
......
......@@ -263,8 +263,10 @@ def detection_output(loc,
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
LoD will be set to {1}, and output tensor only contains one
value, which is -1.
(After version 1.3, when no boxes detected, the lod is changed
from {0} to {1}.)
Examples:
.. code-block:: python
......@@ -1967,8 +1969,8 @@ def multiclass_nms(bboxes,
scores,
score_threshold,
nms_top_k,
nms_threshold,
keep_top_k,
nms_threshold=0.3,
normalized=True,
nms_eta=1.,
background_label=0,
......@@ -2035,8 +2037,10 @@ def multiclass_nms(bboxes,
Each row has 10 values:
[label, confidence, x1, y1, x2, y2, x3, y3, x4, y4]. No is the
total number of detections. If there is no detected boxes for all
images, lod will be set to {0, 1} and Out only contains one value
images, lod will be set to {1} and Out only contains one value
which is -1.
(After version 1.3, when no boxes detected, the lod is changed
from {0} to {1})
Examples:
.. code-block:: python
......
......@@ -19,7 +19,7 @@ import copy
from op_test import OpTest
def iou(box_a, box_b, normalized):
def iou(box_a, box_b, norm):
"""Apply intersection-over-union overlap between box_a and box_b
"""
xmin_a = min(box_a[0], box_a[2])
......@@ -32,10 +32,10 @@ def iou(box_a, box_b, normalized):
xmax_b = max(box_b[0], box_b[2])
ymax_b = max(box_b[1], box_b[3])
area_a = (ymax_a - ymin_a + (normalized == False)) * \
(xmax_a - xmin_a + (normalized == False))
area_b = (ymax_b - ymin_b + (normalized == False)) * \
(xmax_b - xmin_b + (normalized == False))
area_a = (ymax_a - ymin_a + (norm == False)) * (xmax_a - xmin_a +
(norm == False))
area_b = (ymax_b - ymin_b + (norm == False)) * (xmax_b - xmin_b +
(norm == False))
if area_a <= 0 and area_b <= 0:
return 0.0
......@@ -44,8 +44,8 @@ def iou(box_a, box_b, normalized):
xb = min(xmax_a, xmax_b)
yb = min(ymax_a, ymax_b)
inter_area = max(xb - xa + (normalized == False), 0.0) * \
max(yb - ya + (normalized == False), 0.0)
inter_area = max(xb - xa + (norm == False),
0.0) * max(yb - ya + (norm == False), 0.0)
iou_ratio = inter_area / (area_a + area_b - inter_area)
......@@ -210,7 +210,6 @@ def batched_multiclass_nms(boxes,
normalized,
shared=True)
if nmsed_num == 0:
# lod.append(1)
continue
lod.append(nmsed_num)
......
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