Giter Site home page Giter Site logo

YOLOv3导出后的模型如何在Paddle-Lite中使用?完全不知道模型输入输出的接口呀,郁闷呀。 about paddledetection HOT 5 CLOSED

paddlepaddle avatar paddlepaddle commented on May 17, 2024
YOLOv3导出后的模型如何在Paddle-Lite中使用?完全不知道模型输入输出的接口呀,郁闷呀。

from paddledetection.

Comments (5)

zhuyushi avatar zhuyushi commented on May 17, 2024

补充:
下面这个表述有问题:
(1)导出模型的输出是否就是原始YOLOv3模型的输出?为什么我在测试Paddle-Lite自己写的推理程序时,由于少了一个原始图片输入,导致程序core掉,原始YOLOv3模型需要原始图片信息?
应该是:
(1)导出模型的输出是否就是原始YOLOv3模型的输出?为什么我在测试Paddle-Lite自己写的推理程序时,由于少了一个“原始图片尺寸”的输入,导致程序core掉,原始YOLOv3模型的输入需要原始图片尺寸信息?

from paddledetection.

heavengate avatar heavengate commented on May 17, 2024

你好:

  1. 保存的YOLOv3模型的输入是YOLOv3网络要求的输入,即原始图片经过减均值除方差转换为[C, H, W]之后的数据,预处理过程见

    sample_transforms:

    预处理操作的python实现见
    https://github.com/PaddlePaddle/PaddleDetection/blob/master/ppdet/data/transform/operators.py
    基于PaddleLite部署的话,输出数据需要是采用上述预处理之后的图片数据,预测部署预处理的c++代码可以参考
    https://github.com/PaddlePaddle/PaddleDetection/tree/master/inference/preprocessor

  2. 保存模型的输出是已经解析好并做过NMS之后的box信息,输出是一个shape为[N, 6]的数据,其中N为预测框的个数,6为[class_id, score, x1, y1, x2, y2], 输出格式参考
    https://www.paddlepaddle.org.cn/documentation/docs/zh/api_cn/layers_cn/multiclass_nms_cn.html#multiclass-nms
    预测部署输出bbox处理C++代码参考

    void output_detection_result(const float* out_addr,

from paddledetection.

qingqing01 avatar qingqing01 commented on May 17, 2024

@zhuyushi 感谢反馈,我们也会同步增强下文档~

from paddledetection.

jerrywgz avatar jerrywgz commented on May 17, 2024

#241 已在docs/advanced_tutorials/inference/EXPORT_MODEL.md处添加详细的导出模型的输入输出介绍,可以参考

from paddledetection.

Yu-wy avatar Yu-wy commented on May 17, 2024

有paddlex的吗

from paddledetection.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.