Paddle jetson nano上batch=4推理崩溃

cnjp1d6j  于 2021-11-30  发布在  Java
关注(0)|答案(4)|浏览(454)

paddle版本:1.6
错误信息:
W0303 23:24:53.351265 28635 device_context.cc:237] Please NOTE: device: 0, CUDA Capability: 53, Driver API Version: 10.0, Runtime API Version: 10.0
W0303 23:24:53.360337 28635 device_context.cc:245] device: 0, cuDNN Version: 7.5.
Segmentation fault (core dumped)

0ve6wy6x

0ve6wy6x1#

您好,我们已经收到了您的问题,会安排技术人员尽快解答您的问题,请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时,您也可以通过查看官网API文档常见问题历史IssueAI社区来寻求解答。祝您生活愉快~

Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the APIFAQGithub Issue and AI community to get the answer.Have a nice day!

icomxhvb

icomxhvb2#

是指在Nvdia jetson nano型号上运行哪个模型产生问题呢?

pqwbnv8z

pqwbnv8z3#

batch4小于4的时候是否可以正常运行。可以查看是不是显存不足了。

8iwquhpp

8iwquhpp4#

batch1、batch2、batch3都是可以的,batch4就崩溃,显存还剩400M崩溃的。
模型大小如下:
-rw-rw-r-- 1 585K 1月 14 20:55 detection.pdl_model
-rw-rw-r-- 1 235M 1月 14 20:55 detection.pdl_param

相关问题