Comments (8)
iwanggp
commented on May 18, 2024
1
这个用trtexec 命令转换还是有点问题的，现在用代码转换就没问题了。需要重新写一个动态onnx转换的功能就能解决了。用trtexec命令转还是要谨慎。
from tensorrt-alpha.
FeiYull
commented on May 18, 2024
@iwanggp
编译动态onnx的时候，需要设置最大batch_size，例如：将--maxShapes=images:8x3x640x640 修改成：--maxShapes=images:9x3x640x640
from tensorrt-alpha.
iwanggp
commented on May 18, 2024
那使用不同版本的trtexec转换也会有影响吧
from tensorrt-alpha.
iwanggp
commented on May 18, 2024
我之前有个YOLOv8工程用了同样的方法，批处理推理可以成功，但是我将我的YOLOv8项目拷贝到其他的地方，或者加载之前训练的权重继续训练，再转trt时候，就只能获得第一张图片的结果。怎么这么奇怪吗
from tensorrt-alpha.
FeiYull
commented on May 18, 2024
模型不能拷贝到新的环境
FeiYull
***@***.***
…------------------ 原始邮件 ------------------
发件人: 神雕大侠 ***@***.***>
发送时间: 2023年9月8日 17:55
收件人: FeiYull/TensorRT-Alpha ***@***.***>
抄送: FeiYull ***@***.***>, Comment ***@***.***>
主题: Re: [FeiYull/TensorRT-Alpha] 使用批次推理，只有第一张有结果 (Issue #50)
我之前有个YOLOv8工程用了同样的方法，批处理推理可以成功，但是我将我的YOLOv8项目拷贝到其他的地方，或者加载之前训练的权重继续训练，再转trt时候，就只能获得第一张图片的结果。怎么这么奇怪吗
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
from tensorrt-alpha.
iwanggp
commented on May 18, 2024
你说必须在原先的机器上吗？我新拉去个工程，从新训练也不行。这么奇怪吗
from tensorrt-alpha.
FeiYull
commented on May 18, 2024
onnx可以随便拷贝到任何环境中，但是.trt文件不行
FeiYull
***@***.***
…------------------ 原始邮件 ------------------
发件人: 神雕大侠 ***@***.***>
发送时间: 2023年9月8日 18:54
收件人: FeiYull/TensorRT-Alpha ***@***.***>
抄送: FeiYull ***@***.***>, Comment ***@***.***>
主题: Re: [FeiYull/TensorRT-Alpha] 使用批次推理，只有第一张有结果 (Issue #50)
from tensorrt-alpha.
iwanggp
commented on May 18, 2024
就是转换必须要在当前机器上进行转换吗？我这是同一个机器就是拷贝同一份再训练发现结果无论如何对不齐，trt只有第一张图片有结果。
from tensorrt-alpha.
Related Issues (20)
- yolov8 obb HOT 1
- yolov8 vs项目生成报错 HOT 2
- 编译失败
- 如何计算转化后mAP值 HOT 1
- yolov8-pose推理时报错 HOT 1
- support yolo-world
- 抓狂，过了一夜报错:UDA initialization failure with error: 222.，之前还是跑通的
- 自己训练的模型检测框错位，标签乱 HOT 1
- Cuda12.1+tensorrt10.0 运行C++yolov8工程报错，提示getBindingDimensions 不是 nvinfer1::IExecutionContext成员 代码C2039 HOT 3
- spend more than 20ms on prepocess on jetson nano, batch=1 HOT 7
- make -j10在jetson nano上报错
- 希望后期可以支持目标跟踪 HOT 1
- onnx转换trt报错 HOT 1
- YOLOV8-SEG 如何快速获取mask掩码 HOT 6
- Windows Cmake编译错误 HOT 6
- Yolov8部署jetson后map精度问题
- v8-pose在Jetson AGX Xavier上的推理时间问题 HOT 1
- 期待加上目标跟踪功能
- YOLOv8-pose 出现编译错误 ，up帮忙看看给您磕头了 HOT 1
- yolov8 seg output有output0和output1，代码中使用output0有问题 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorrt-alpha.