crosstyan/RapidPoseTriangulation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Further small improvements.

Browse Source
This commit is contained in:
Daniel
2024-12-06 18:15:08 +01:00
parent ee8b9bafb3
commit 23108dd594
4 changed files with 179 additions and 170 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
extras/mmdeploy/configs/detection_onnxruntime_static-320x320.py
View File

@ -7,12 +7,12 @@ onnx_config = dict(
codebase_config = dict(
# For later TensorRT inference, the number of output boxes needs to be as stable as possible,
# because a drop in the box count leads to a re-optimization which takes a lot of time,
# therefore sort out low confidence boxes outside the model and reduce the maximum number
# of output boxes to the smallest usable value.
# therefore reduce the maximum number of output boxes to the smallest usable value and sort out
# low confidence boxes outside the model.
post_processing=dict(
score_threshold=0.0,
confidence_threshold=0.0,
iou_threshold=0.3,
iou_threshold=0.5,
max_output_boxes_per_class=10,
),
)