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

feat: add new traffic light detector artifacts download #5626

Closed
wants to merge 4 commits into from
Closed

feat: add new traffic light detector artifacts download #5626

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3eb256d
feat: add new tl detector artifacts download
badai-nguyen Jan 6, 2025
5b0c5ca
Merge branch 'main' into feat/add_new_tl_detector_onnx_donwload
badai-nguyen Jan 22, 2025
213f6a7
Merge branch 'main' into feat/add_new_tl_detector_onnx_donwload
badai-nguyen Jan 28, 2025
03e193c
chore: fix cspell
badai-nguyen Jan 28, 2025
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
25 changes: 25 additions & 0 deletions ansible/roles/artifacts/tasks/main.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,14 +261,39 @@
mode: "644"
checksum: sha256:28cd6524d4bcdb2809592a225d28330433e58dc02c92169ea555b44c1a51a584

- name: Download tensorrt_yolox/semseg_color_map.csv

Check warning on line 264 in ansible/roles/artifacts/tasks/main.yaml

View workflow job for this annotation

GitHub Actions / spell-check-differential 

Unknown word (semseg)
become: true
ansible.builtin.get_url:
url: https://awf.ml.dev.web.auto/perception/models/object_detection_semseg_yolox_s/v1/semseg_color_map.csv
dest: "{{ data_dir }}/tensorrt_yolox/semseg_color_map.csv"

Check warning on line 268 in ansible/roles/artifacts/tasks/main.yaml

View workflow job for this annotation

GitHub Actions / spell-check-differential 

Unknown word (semseg)
mode: "644"
checksum: sha256:3d93ca05f31b63424d7d7246a01a2365953705a0ed3323ba5b6fddd744a4bfea

# traffic_light_detector model which referenced by tensorrt_yolox package
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[imho]
We need to clearfy which tlr model will be downloaded in this role.
Do we have our new model name already? How about one-shot traffic_light_detector model?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@YoshiRi

We need to clearfy which tlr model will be downloaded in this role.

all model listed here will be downloaded when setup autoware as default. The used model whill be selected by seting when launching autoware.

Do we have our new model name already? How about one-shot traffic_light_detector model?

  • The current selected name is yolox_s_car_ped_tl_detector_960_960_batch_1
  • I think all current yolox only support one-shot so it seems unnecessary?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@YoshiRi do you hav another comments?

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@YoshiRi
The name whole_image_traffic_light_detector is good to look good to me considering launcher params.
So I think comment out is # tensorrt_yolox for whole_image_traffic_light_detector to look good to me. What do you think?

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@badai-nguyen @MasatoSaeki Now I understood. LGTM

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
# traffic_light_detector model which referenced by tensorrt_yolox package
# tensorrt_yolox for whole_image_traffic_light_detector

- name: Download tensorrt_yolox/yolox_s_car_ped_tl_detector_960_960_batch_1.onnx
become: true
ansible.builtin.get_url:
url: https://awf.ml.dev.web.auto/perception/models/tl_detector_yolox_s/v1/yolox_s_car_ped_tl_detector_960_960_batch_1.onnx
dest: "{{ data_dir }}/tensorrt_yolox/yolox_s_car_ped_tl_detector_960_960_batch_1.onnx"
mode: "644"
checksum: sha256:0b8478553f2f0374a1236e65f669f11335b1fea7756ca7bcdfcf9646657ed594

- name: Download tensorrt_yolox/yolox_s_car_ped_tl_detector_960_960_batch_1.EntropyV2-calibration.table
become: true
ansible.builtin.get_url:
url: https://awf.ml.dev.web.auto/perception/models/tl_detector_yolox_s/v1/yolox_s_car_ped_tl_detector_960_960_batch_1.EntropyV2-calibration.table
dest: "{{ data_dir }}/tensorrt_yolox/yolox_s_car_ped_tl_detector_960_960_batch_1.EntropyV2-calibration.table"
mode: "644"
checksum: sha256:690cff409519aca26f4ec0fc56ed35d9aa23ee1c18d6205c43469ae06e2f4e02

- name: Download tensorrt/car_ped_tl_detector_labels.txt
become: true
ansible.builtin.get_url:
url: https://awf.ml.dev.web.auto/perception/models/tl_detector_yolox_s/v1/car_ped_tl_detector_labels.txt
dest: "{{ data_dir }}/tensorrt_yolox/car_ped_tl_detector_labels.txt"
mode: "644"
checksum: sha256:a2a91f5fe9c2e68e3e3647a272bb9bb25cd07631a1990a3fb15efddce7691131

# traffic_light_classifier
- name: Create traffic_light_classifier directory inside {{ data_dir }}
ansible.builtin.file:
Expand Down
Loading