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

Implement strided_transformer_pose3d #920

Open
wants to merge 10 commits into
base: master
Choose a base branch
from

Conversation

hattan1990
Copy link
Contributor

No description provided.

@kyakuno
Copy link
Collaborator

kyakuno commented Sep 26, 2022

モデルアップロード済み。

@kyakuno
Copy link
Collaborator

kyakuno commented Oct 15, 2022

@hattan1990 少しlibフォルダの下のコードが複雑なので、strided_transformer_pose3d_util.pyに収まるぐらいに整理していただけますでしょうか。

(1) yoloxの前処理と後処理をailia.Detectorに置き換え(detector.compute(raw_img, args.threshold, args.iou)を参照してください https://github.com/axinc-ai/ailia-models/blob/master/object_detection/yolox/yolox.py)
(2) hrnetフォルダ以下のyamlを削除したい(必要な設定はサンプルのpythonコードに最小限をハードコードしたい)

@hattan1990
Copy link
Contributor Author

@kyakuno
(1)と(2)の対応が完了いたしました。

@kyakuno
Copy link
Collaborator

kyakuno commented Mar 5, 2024

filterpyが必要。

@kyakuno
Copy link
Collaborator

kyakuno commented Mar 5, 2024

webカメラで人がいなくなると下記のエラーになる。

Traceback (most recent call last):
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/strided_transformer_pose3d.py", line 169, in <module>
    main()
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/strided_transformer_pose3d.py", line 162, in main
    recognize_from_video()
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/strided_transformer_pose3d.py", line 133, in recognize_from_video
    image_pose2d, ax_pose3d, detect_flg = detect(frame, net_yolo, net_pose2d, net_pose3d, fig)
                                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/lib/run.py", line 204, in detect
    keypoints = get_pose2D(human_model, pose_model2d, img)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/lib/run.py", line 126, in get_pose2D
    keypoints, scores = hrnet_pose(img, human_model, pose_model, det_dim=416, num_peroson=1)
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/lib/gen_kpts.py", line 455, in gen_video_kpts
    people_track = people_sort.update(bboxs)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/lib/gen_kpts.py", line 407, in update
    trk = KalmanBoxTracker(dets[i, :])
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/lib/gen_kpts.py", line 283, in __init__
    self.kf.x[:4] = convert_bbox_to_z(bbox)
                    ^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/kyakuno/Desktop/ailia/ailia-models-ax/pose_estimation_3d/strided_transformer_pose3d/lib/gen_kpts.py", line 237, in convert_bbox_to_z
    w = bbox[2] - bbox[0]
        ~~~~^^^
IndexError: index 2 is out of bounds for axis 0 with size 0

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants