Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
Warning: Unable to use numba in PP-Tracking, please install numba, for example(python3.7): `pip install numba==0.56.4`
Warning: Unable to use numba in PP-Tracking, please install numba, for example(python3.7): `pip install numba==0.56.4`
Warning: import ppdet from source directory without installing, run 'python setup.py install' to install ppdet firstly
W1209 19:56:01.282155 15045 gpu_resources.cc:96] The GPU architecture in your current machine is Pascal, which is not compatible with Paddle installation with arch: 70 75 80 86 , it is recommended to install the corresponding wheel package according to the installation information on the official Paddle website.
W1209 19:56:01.282171 15045 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 11.4, Runtime API Version: 11.4
W1209 19:56:01.284783 15045 gpu_resources.cc:149] device: 0, cuDNN Version: 8.2.
[12/09 19:56:01] ppdet.utils.checkpoint INFO: Finish loading model weights: output/ppyoloe_r_crn_s_3x_dota_ms_clamp_wire-360epochs0.797/best_model.pdparams
[12/09 19:56:01] train INFO: Found 59 inference images in total.
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 30/30 [00:02<00:00, 11.96it/s]
[12/09 19:56:04] ppdet.engine INFO: Detection bbox results save in output/52.jpg
[12/09 19:56:04] ppdet.engine INFO: Detection bbox results save in output/106.jpg
[12/09 19:56:04] ppdet.engine INFO: Detection bbox results save in output/146.jpg
[12/09 19:56:04] ppdet.engine INFO: Detection bbox results save in output/94.jpg
[12/09 19:56:04] ppdet.engine INFO: Detection bbox results save in output/290.jpg
[12/09 19:56:04] ppdet.engine INFO: Detection bbox results save in output/205.jpg
问题确认 Search before asking
请提出你的问题 Please ask your question
PPYOLOE_R训练完毕,执行预测命令:
1、NVIDIA RTX A6000 48G硬件下推理正常,有预测框: 2、但是,在NVIDIA GTX 1060 6G硬件下推理出错,没有预测框: 此时,推理信息:
环境: RTX A6000 ubuntu20.04/GTX1060 ubuntu18.04 paddle2.5.2 paddledetection2.6 python3.7.13
望大佬解答,谢谢。