Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
ResNet50_tensorflow
Commits
cebdd86f
Commit
cebdd86f
authored
Jul 09, 2021
by
The-Indian-Chinna
Browse files
Minor: changed documentation for nms functions.
parent
ff17727b
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
5 deletions
+5
-5
official/vision/beta/projects/yolo/ops/nms_ops.py
official/vision/beta/projects/yolo/ops/nms_ops.py
+5
-5
No files found.
official/vision/beta/projects/yolo/ops/nms_ops.py
View file @
cebdd86f
...
...
@@ -365,7 +365,10 @@ def sort_drop(objectness, box, classificationsi, k):
def
segment_nms
(
boxes
,
classes
,
confidence
,
k
,
iou_thresh
):
"""This is a quick nms that works on very well for small values of k, this
"""non max-suppression used to filter predicted boxes that doesn't account
for classes.
This is a quick nms that works on very well for small values of k, this
was developed to operate for tflite models as the tiled NMS is far too slow
and typically is not able to compile with tflite. This NMS does not account
for classes, and only works to quickly filter boxes on phones.
...
...
@@ -417,10 +420,7 @@ def nms(boxes,
pre_nms_thresh
,
nms_thresh
,
prenms_top_k
=
500
):
"""This is a quick nms that works on very well for small values of k, this
was developed to operate for tflite models as the tiled NMS is far too slow
and typically is not able to compile with tflite. This NMS does not account
for classes, and only works to quickly filter boxes on phones.
"""Tiled non max-suppression used to filter predicted boxes.
Args:
boxes: a `Tensor` of shape [batch size, N, 4] that needs to be filtered.
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment