Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Apache License 2.0
12.69k
stars
2.87k
forks
source link
When running on GPU, I get normalized bboxes, when running on CPU, bbox in the desired format #8258
问题确认 Search before asking
请提出你的问题 Please ask your question
I run docker image from hub
paddlepaddle/paddle:2.5.0rc0-gpu-cuda11.7-cudnn8.4-trt8.4
After i want to run deploy model like this:On inference_model/detectioni have inference model (pdmodle, pdiparms and so on), also infer_cfg.yml:
and after running i get like this bboxes like this:
BUT If i change device to CPU i get correct bbox like this:
class_id:0, confidence:0.9976, left_top:[839.24,542.89],right_bottom:[1906.61,1511.53
]