PaddlePaddle/PaddleDetection

模型对象作为参数传入到回调函数里无法调用GPU？

Open

#3,925 opened on Aug 10, 2021

View on GitHub
 (4 comments) (0 reactions) (0 assignees)Python (11,414 stars) (2,731 forks)batch import
help wanted

Description

业务需求中存在回调函数，数据源来源回调函数，因此需要把模型初始化放在主函数，推理部分通过传参进入回调函数进行推理，这样做代码可以跑，但是无法调用GPU，把推理函数放到主函数内推理就可以调用GPU，因此不知道如何解决在回调函数内进行推理无法调用GPU的问题如何解决？

Contributor guide

Tech stack
python
Domain
machine learning
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
needs investigation
Prerequisites
basic PaddlePaddle knowledgeGPU acceleration basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25
Research direction
Investigate how PaddlePaddle handles GPU context when a model is passed as an argument to a callback function. Check if the model's GPU context is lost or if there is a need to explicitly move the model to GPU within the callback. Look at PaddlePaddle documentation and existing issues related to callbacks and GPU usage.