Coder Social home page Coder Social logo

Comments (7)

JiaPai12138 avatar JiaPai12138 commented on May 15, 2024 2

补充:
Tensorrt 8.2.5.1 不会出现任何警告
但实际上可以通过

logger = trt.Logger(trt.Logger.WARNING)
logger.min_severity = trt.Logger.Severity.ERROR
runtime = trt.Runtime(logger)

来取消警告显示

但是 Tensorrt 8.2 和 Tensorrt 8.4 量化的模型不能通用 (8.4下生成的模型无法用 8.2 的依赖推理)
测试下 8.4 生成的模型体积较小 (体积大约是8.2生成的86.8%), 并且最终推理速度快大约 7.5%
测试的模型为 yolov6n 416*416, fp32, 显卡为 GTX 1660 ti max q, 语言为py(完全是本仓库源码)

from tensorrt-for-yolo-series.

JiaPai12138 avatar JiaPai12138 commented on May 15, 2024

降到cudnn 8.2.4 就可以继续运行了

CUDA 11.4~11.6 都可行
Tensorrt 8.2 ~ 8.4 都测试可行, 建议 8.4

from tensorrt-for-yolo-series.

Linaom1214 avatar Linaom1214 commented on May 15, 2024

重新开启了这个issue,希望有同样问题的同学可以看到。

from tensorrt-for-yolo-series.

Linaom1214 avatar Linaom1214 commented on May 15, 2024

补充: Tensorrt 8.2.5.1 不会出现任何警告 但是 Tensorrt 8.2 和 Tensorrt 8.4 量化的模型不能通用 (8.4下生成的模型无法用 8.2 的依赖推理) 测试下 8.4 生成的模型体积较小 (体积大约是8.2生成的86.8%), 并且最终推理速度快大约 7.5% 测试的模型为 yolov6n 416*416, fp32, 显卡为 GTX 1660 ti max q

最后是使用Python还是c++做部署呢?

from tensorrt-for-yolo-series.

JiaPai12138 avatar JiaPai12138 commented on May 15, 2024

补充: Tensorrt 8.2.5.1 不会出现任何警告 但是 Tensorrt 8.2 和 Tensorrt 8.4 量化的模型不能通用 (8.4下生成的模型无法用 8.2 的依赖推理) 测试下 8.4 生成的模型体积较小 (体积大约是8.2生成的86.8%), 并且最终推理速度快大约 7.5% 测试的模型为 yolov6n 416*416, fp32, 显卡为 GTX 1660 ti max q

最后是使用Python还是c++做部署呢?

py部署 用您的源码
我的垃圾显卡达到400 fps

from tensorrt-for-yolo-series.

1994sugar avatar 1994sugar commented on May 15, 2024

补充: Tensorrt 8.2.5.1 不会出现任何警告 但是 Tensorrt 8.2 和 Tensorrt 8.4 量化的模型不能通用 (8.4下生成的模型无法用 8.2 的依赖推理) 测试下 8.4 生成的模型体积较小 (体积大约是8.2生成的86.8%), 并且最终推理速度快大约 7.5% 测试的模型为 yolov6n 416*416, fp32, 显卡为 GTX 1660 ti max q

最后是使用Python还是c++做部署呢?

py部署 用您的源码 我的垃圾显卡达到400 fps
您好,您用py部署时是与flask一起使用的吗?

from tensorrt-for-yolo-series.

JiaPai12138 avatar JiaPai12138 commented on May 15, 2024

20221115更新(这问题可以置顶么23333):
CUDA11.4-11.7 Cudnn 8.4
下载这个官方文档里指示的文件并解压
将其中的zlibwapi.dll复制到CUDA安装目录下的bin文件夹内
见证奇迹的时刻~~

from tensorrt-for-yolo-series.

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.