AXERA-TECH/ax-samples

仿真正常运行,然后网络结构一样,板子运行报错

dragonforward opened this issue · 0 comments

工具:ax_pulsar2_1.9_enc.tar.gz
板子镜像:1.27
在pulsar2中仿真运行正常:
root@565473f6ba23:/data/pulsar2-run-helper# python3 cli_detection.py --post_processing --image_path sim_images/000032.jpg --axmodel_path models/yolov5s_hat.axmodel --intermediate_path sim_outputs/0
[I] Number of detected objects: 7
[I] 0: 94.59%, [972, 224, 1089, 345]
[I] 0: 94.56%, [886, 222, 970, 327]
[I] 0: 94.12%, [1141, 145, 1262, 281]
[I] 0: 93.96%, [487, 249, 571, 370]
[I] 0: 93.94%, [331, 201, 430, 341]
[I] 0: 93.27%, [186, 192, 302, 351]
[I] 0: 62.17%, [607, 233, 692, 338]

修改axsample中ax_yolov5s_steps.cc的class文件改为自己的,然后执行./ax_yolov5s -m yolov5s_hat.axmodel -i 000032.jpg

报错如下:
WARN,Func(__is_valid_file),NOT find file = '/etc/ax_syslog.conf'
ERROR,Func(__syslog_parma_cfg_get), NOT find = '/etc/ax_syslog.conf'
Engine creating handle is done.
Engine creating context is done.
Engine get io info is done.
Engine alloc io is done.
Engine push input is done.

Segmentation fault