Comments (5)
Have you tried the official model?
from tensorrtx.
Have you tried the official model?
Yes, I used the yolov8 official weight pt(yolov8s-seg.pt) to convert
from tensorrtx.
@Rex-LK Please take a look.
from tensorrtx.
我用官方模型(640 X 640)和自己做的模型(640 X 640)不会报这个错误,用自己做的模型(960 X 960)也报这个错误:
[11/20/2023-15:58:28] [E] [TRT] 4: [shapeContext.cpp::nvinfer1::builder::reshapeCanFaultHelper::<lambda_87ad3b929fe52b49c0129bfe558f8fdd>::operator ()::3546] Error Code 4: Shape Error (reshape changes volume. Reshaping [32,120,120] to [32,6400].)
[11/20/2023-15:58:28] [E] [TRT] 4: [network.cpp::nvinfer1::Network::validate::2977] Error Code 4: Internal Error (Could not compute dimensions for (Unnamed Layer* 317) [Shuffle]_output, because the network is not valid.)
请问是需要修改哪边适配别的模型输入尺寸吗?
from tensorrtx.
我用官方模型(640 X 640)和自己做的模型(640 X 640)不会报这个错误,用自己做的模型(960 X 960)也报这个错误: [11/20/2023-15:58:28] [E] [TRT] 4: [shapeContext.cpp::nvinfer1::builder::reshapeCanFaultHelper::<lambda_87ad3b929fe52b49c0129bfe558f8fdd>::operator ()::3546] Error Code 4: Shape Error (reshape changes volume. Reshaping [32,120,120] to [32,6400].) [11/20/2023-15:58:28] [E] [TRT] 4: [network.cpp::nvinfer1::Network::validate::2977] Error Code 4: Internal Error (Could not compute dimensions for (Unnamed Layer* 317) [Shuffle]_output, because the network is not valid.)
请问是需要修改哪边适配别的模型输入尺寸吗?
maybe you can try to modify the config.h file in src directory
from tensorrtx.
Related Issues (20)
- Fix issue in boxes calculation in 'rcnn/PredictorDecode.cu' HOT 2
- infer without results HOT 1
- INT8量化问题:最后输出模型时报错,提示"[E] [TRT] 1: Unexpected exception invalid unordered_map<K, T> key" HOT 4
- Nothing can be predicted after changing the code HOT 8
- yolov5 int8量化推理结果为空 HOT 6
- yolov8 TRT问题 HOT 5
- 从wts文件读取权重数据,应该是hex的float值, 为什么存储在 uint32_t中啊 HOT 2
- 为什么yolov8中,trtx的bottleneck实现与源码不同? 是有特殊的考虑吗?
- Are there any plans to implement support for YOLO-NAS? HOT 2
- Segmentation fault when generate engine HOT 2
- NameError: name 'false' is not defined when I try to generate .wts HOT 2
- Request for Dockerfile of Tensorrtx Image HOT 2
- Depedency Issue : Mxnet-Numpy HOT 4
- The yolov8n inference and post-processing time increases at the time of processing up to the 20th image and remains HOT 3
- yolov5 编译错误 HOT 2
- serialize engine from yolov8l-seg.wts failed! HOT 1
- yolov8s在960x960输入size存在较大概率误检,同一个模型用onnx或者torch推理正常的 HOT 6
- yolov5s.wts读取时出现报错:Segmentation fault HOT 4
- retinaface序列化时的报错 HOT 3
- 尝试修改输入分辨率后,pt转wts报错 HOT 5
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 tensorrtx.