Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(tensorrt_yolox): add data_path arg and update default model path #5119

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions perception/tensorrt_yolox/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ those are labeled as `UNKNOWN`, while detected rectangles are drawn in the visua

## Onnx model

A sample model (named `yolox-tiny.onnx`) is downloaded automatically during the build process.
A sample model (named `yolox-tiny.onnx`) is downloaded by ansible script on env preparation stage, if not, please, follow [Manual downloading of artifacts](https://github.com/autowarefoundation/autoware/tree/main/ansible/roles/artifacts).
To accelerate Non-maximum-suppression (NMS), which is one of the common post-process after object detection inference,
`EfficientNMS_TRT` module is attached after the ordinal YOLOX (tiny) network.
The `EfficientNMS_TRT` module contains fixed values for `score_threshold` and `nms_threshold` in it,
Expand Down Expand Up @@ -146,7 +146,7 @@ Please refer [the official document](https://github.com/Megvii-BaseDetection/YOL

## Label file

A sample label file (named `label.txt`)is also downloaded automatically during the build process
A sample label file (named `label.txt`)is also downloaded automatically during env preparation process
(**NOTE:** This file is incompatible with models that output labels for the COCO dataset (e.g., models from the official YOLOX repository)).

This file represents the correspondence between class index (integer outputted from YOLOX network) and
Expand Down
3 changes: 2 additions & 1 deletion perception/tensorrt_yolox/launch/yolox_s_plus_opt.launch.xml
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,8 @@
<arg name="input/image" default="/sensing/camera/camera0/image_rect_color"/>
<arg name="output/objects" default="/perception/object_recognition/detection/rois0"/>
<arg name="model_name" default="yolox-sPlus-T4-960x960-pseudo-finetune"/>
<arg name="model_path" default="$(find-pkg-share tensorrt_yolox)/data"/>
<arg name="data_path" default="$(env HOME)/autoware_data" description="packages data and artifacts directory path"/>
<arg name="model_path" default="$(var data_path)/tensorrt_yolox"/>
<arg name="score_threshold" default="0.35"/>
<arg name="nms_threshold" default="0.7"/>
<arg name="precision" default="int8" description="operation precision to be used on inference. Valid value is one of: [fp32, fp16, int8]"/>
Expand Down
3 changes: 2 additions & 1 deletion perception/tensorrt_yolox/launch/yolox_tiny.launch.xml
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,8 @@
<arg name="input/image" default="/sensing/camera/camera0/image_rect_color"/>
<arg name="output/objects" default="/perception/object_recognition/detection/rois0"/>
<arg name="model_name" default="yolox-tiny"/>
<arg name="model_path" default="$(find-pkg-share tensorrt_yolox)/data"/>
<arg name="data_path" default="$(env HOME)/autoware_data" description="packages data and artifacts directory path"/>
<arg name="model_path" default="$(var data_path)/tensorrt_yolox"/>
<arg name="score_threshold" default="0.35"/>
<arg name="nms_threshold" default="0.7"/>
<arg name="precision" default="fp16" description="operation precision to be used on inference. Valid value is one of: [fp32, fp16, int8]"/>
Expand Down