Unable to run PPHuman #9306
Description
问题确认 Search before asking
Bug组件 Bug Component
No response
Bug描述 Describe the Bug
I'm trying to run pphuman by following the steps mention here pptracking
but getting below error
python deploy/pptracking/python/mot_sde_infer.py --model_dir=output_inference/ppyolov2_r50vd_dcn_365e_aic21mtmct_vehicle/ --reid_model_dir=output_inference/deepsort_pplcnet_vehicle/ --mtmct_dir=./mtmct-demo --device=GPU --mtmct_cfg=deploy/pptracking/python/mtmct_cfg.yml --scaled=True --save_mot_txts --save_images --tracker_config=deploy/pptracking/python/tracker_config.yml
Warning: Unable to use motmetrics in MTMCT in PP-Tracking, please install motmetrics, for example: `pip install motmetrics`, see https://github.com/longcw/py-motmetrics
----------- Running Arguments -----------
batch_size: 1
camera_id: -1
cpu_threads: 1
device: GPU
do_break_in_counting: False
do_entrance_counting: False
draw_center_traj: False
enable_mkldnn: False
image_dir: None
image_file: None
model_dir: output_inference/ppyolov2_r50vd_dcn_365e_aic21mtmct_vehicle/
mtmct_cfg: deploy/pptracking/python/mtmct_cfg.yml
mtmct_dir: ./mtmct-demo
output_dir: output
region_polygon: []
region_type: horizontal
reid_batch_size: 50
reid_model_dir: output_inference/deepsort_pplcnet_vehicle/
run_benchmark: False
run_mode: paddle
save_images: True
save_mot_txt_per_img: False
save_mot_txts: True
scaled: True
secs_interval: 2
skip_frame_num: -1
threshold: 0.5
tracker_config: deploy/pptracking/python/tracker_config.yml
trt_calib_mode: False
trt_max_shape: 1280
trt_min_shape: 1
trt_opt_shape: 640
use_dark: True
use_gpu: False
video_file: None
warmup_frame: 50
------------------------------------------
----------- Model Configuration -----------
Model Arch: YOLO
Transform Order:
--transform op: Resize
--transform op: NormalizeImage
--transform op: Permute
--------------------------------------------
----------- Model Configuration -----------
Model Arch: DeepSORT
Transform Order:
--transform op: LetterBoxResize
--transform op: NormalizeImage
--transform op: Permute
--------------------------------------------
start tracking seq: c003
Tracking frame: 0
Traceback (most recent call last):
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot_sde_infer.py", line 953, in <module>
main()
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot_sde_infer.py", line 922, in main
detector.predict_mtmct(FLAGS.mtmct_dir, mtmct_cfg)
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot_sde_infer.py", line 830, in predict_mtmct
mot_features_dict = self.predict_image(
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot_sde_infer.py", line 563, in predict_image
tracking_outs = self.tracking(det_result)
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot_sde_infer.py", line 319, in tracking
online_targets = self.tracker.update(pred_dets, pred_embs)
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot/tracker/deepsort_tracker.py", line 114, in update
self.tracks[track_idx].update(self.motion,
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot/tracker/base_sde_tracker.py", line 122, in update
self.mean, self.covariance = kalman_filter.update(self.mean,
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot/motion/kalman_filter.py", line 255, in update
projected_mean, projected_cov = self.project(mean, covariance)
File "/home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot/motion/kalman_filter.py", line 184, in project
return nb_project(mean, covariance, std, self._update_mat)
File "/home/mustak/miniconda3/envs/det1/lib/python3.10/site-packages/numba/core/dispatcher.py", line 468, in _compile_for_args
error_rewrite(e, 'typing')
File "/home/mustak/miniconda3/envs/det1/lib/python3.10/site-packages/numba/core/dispatcher.py", line 409, in error_rewrite
raise e.with_traceback(None)
numba.core.errors.TypingError: Failed in nopython mode pipeline (step: nopython frontend)
No implementation of function Function(<function dot at 0x7183d7f86d40>) found for signature:
>>> dot(array(float32, 2d, C), array(float64, 2d, C))
There are 4 candidate implementations:
- Of which 4 did not match due to:
Overload in function '_OverloadWrapper._build.<locals>.ol_generated': File: numba/core/overload_glue.py: Line 129.
With argument(s): '(array(float32, 2d, C), array(float64, 2d, C))':
Rejected as the implementation raised a specific error:
TypingError: np.dot() arguments must all have the same dtype
raised from /home/mustak/miniconda3/envs/det1/lib/python3.10/site-packages/numba/core/typing/npydecl.py:915
During: resolving callee type: Function(<function dot at 0x7183d7f86d40>)
During: typing of call at /home/mustak/detection/new/PaddleDetection/deploy/pptracking/python/mot/motion/kalman_filter.py (29)
File "deploy/pptracking/python/mot/motion/kalman_filter.py", line 29:
def nb_project(mean, covariance, std, _update_mat):
<source elided>
mean = np.dot(_update_mat, mean)
covariance = np.dot(np.dot(_update_mat, covariance), _update_mat.T)
^
复现环境 Environment
- OS: Linux
- Paddlepaddle-gpu- 2.6.2.post120
- PaddleDetection: release/2.8
- Python: 3.10
- CUDA: 12.2
- GCC: 14.2.0
Bug描述确认 Bug description confirmation
- 我确认已经提供了Bug复现步骤、代码改动说明、以及环境信息，确认问题是可以复现的。I confirm that the bug replication steps, code change instructions, and environment information have been provided, and the problem can be reproduced.
是否愿意提交PR？ Are you willing to submit a PR?
- 我愿意提交PR！I'd like to help by submitting a PR!