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.

Sign up for GitHub

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(traffic_light_ssd_fine_detector): add arg data_path, update model file path #5141

Merged
merged 3 commits into from
Sep 28, 2023
Merged

fix(traffic_light_ssd_fine_detector): add arg data_path, update model file path #5141

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1cfd28b
fix(traffic_light_ssd_fine_detector): add arg data_path, update model…
lexavtanke Sep 26, 2023
d38672f
fix(traffic_light_ssd_fine_detector): update README with data_path arg
lexavtanke Sep 26, 2023
109e104
style(pre-commit): autofix
pre-commit-ci[bot] Sep 26, 2023
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
19 changes: 10 additions & 9 deletions perception/traffic_light_ssd_fine_detector/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,15 +122,16 @@ Based on the camera image and the global ROI array detected by `map_based_detect

### Node Parameters

| Name | Type | Default Value | Description |
| ------------------ | ------ | ------------------------------ | -------------------------------------------------------------------- |
| `onnx_file` | string | "./data/mb2-ssd-lite-tlr.onnx" | The onnx file name for yolo model |
| `label_file` | string | "./data/voc_labels_tl.txt" | The label file with label names for detected objects written on it |
| `dnn_header_type` | string | "pytorch" | Name of DNN trained toolbox: "pytorch" or "mmdetection" |
| `mode` | string | "FP32" | The inference mode: "FP32", "FP16", "INT8" |
| `max_batch_size` | int | 8 | The size of the batch processed at one time by inference by TensorRT |
| `approximate_sync` | bool | false | Flag for whether to ues approximate sync policy |
| `build_only` | bool | false | shutdown node after TensorRT engine file is built |
| Name | Type | Default Value | Description |
| ------------------ | ------ | ------------------------------------------------------------------------ | -------------------------------------------------------------------- |
| `data_path` | string | "$(env HOME)/autoware_data" | packages data and artifacts directory path |
| `onnx_file` | string | "$(var data_path)/traffic_light_ssd_fine_detector/mb2-ssd-lite-tlr.onnx" | The onnx file name for yolo model |
| `label_file` | string | "$(var data_path)/traffic_light_ssd_fine_detector/voc_labels_tl.txt" | The label file with label names for detected objects written on it |
| `dnn_header_type` | string | "pytorch" | Name of DNN trained toolbox: "pytorch" or "mmdetection" |
| `mode` | string | "FP32" | The inference mode: "FP32", "FP16", "INT8" |
| `max_batch_size` | int | 8 | The size of the batch processed at one time by inference by TensorRT |
| `approximate_sync` | bool | false | Flag for whether to ues approximate sync policy |
| `build_only` | bool | false | shutdown node after TensorRT engine file is built |

## Assumptions / Known limits

Expand Down
5 changes: 3 additions & 2 deletions perception/traffic_light_ssd_fine_detector/launch/traffic_light_ssd_fine_detector.launch.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
<launch>
<arg name="onnx_file" default="$(find-pkg-share traffic_light_ssd_fine_detector)/data/mb2-ssd-lite-tlr.onnx"/>
<arg name="label_file" default="$(find-pkg-share traffic_light_ssd_fine_detector)/data/voc_labels_tl.txt"/>
<arg name="data_path" default="$(env HOME)/autoware_data" description="packages data and artifacts directory path"/>
<arg name="onnx_file" default="$(var data_path)/traffic_light_ssd_fine_detector/mb2-ssd-lite-tlr.onnx"/>
<arg name="label_file" default="$(var data_path)/traffic_light_ssd_fine_detector/voc_labels_tl.txt"/>
<arg name="mode" default="FP32"/>
<arg name="dnn_header_type" default="pytorch" description="pytorch or mmdetection"/>
<arg name="input/image" default="/image_raw"/>
Expand Down