PaddleDetection icon indicating copy to clipboard operation
PaddleDetection copied to clipboard

paddle_inference 多线程推理maskrcnn使用PredictorPool内存泄漏!

Open baiyang993 opened this issue 1 year ago • 0 comments

问题确认 Search before asking

  • [X] 我已经查询历史issue,没有发现相似的bug。I have searched the issues and found no similar bug report.

Bug组件 Bug Component

No response

Bug描述 Describe the Bug

使用maskrcnn使用进行多线程推理,使用predictors = PredictorPool(config, model_thread_num) 创建模型,使用predictors.retrive(_model_thread)推理,内存不断上涨,并且log中抓到了报错信息,对上涨的内存段进行抓取line时,也抓到了和log中一样的报错信息。 这是代码: image PaddlePredictors是我们封装好的接口,已经确定没有问题。这是log中抓到的信息: image 这是从内存中抓到的line: 3f46cc6246bea8c578e616c478383cc

复现环境 Environment

OS: Linux PaddleDetection: release/2.4- Python: 3.8.0 CUDA: 11.2

Bug描述确认 Bug description confirmation

  • [X] 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?

  • [X] 我愿意提交PR!I'd like to help by submitting a PR!

baiyang993 avatar Jun 15 '23 09:06 baiyang993