Comments (8)
You can try to debug it by getting the output of middle layers.
from tensorrtx.
You can try to debug it by getting the output of middle layers.
Sorry, I'm a newbie, I don't quite understand what you mean, could you be more detailed, thank you.
from tensorrtx.
For example, you have added 10 layers, from layer1 to layer10, now you only check the output tensor of layer10, and the result is wrong.
For debug purpose, you can first get the output of layer1, to see if the result is correct. If yes, then check layer2.
Check the layer output one by one, until you found which layer has issue.
from tensorrtx.
For example, you have added 10 layers, from layer1 to layer10, now you only check the output tensor of layer10, and the result is wrong.
For debug purpose, you can first get the output of layer1, to see if the result is correct. If yes, then check layer2. Check the layer output one by one, until you found which layer has issue.
Hello, the modified model is the same as the original model. The Dimensions, DynamicRangeMin, DynamicRangeMax, and AllowedFormats of each layer's tensors are the same. What output should I check? If all the outputs are the same, what should I do?
from tensorrtx.
Have you check the values of the output tensor for each layer?
from tensorrtx.
Dimensions、DynamicRangeMin、DynamicRangeMax和AllowedFormats
Yes, I have checked every layer, including tensor Dimensions, DynamicRangeMin, DynamicRangeMax and AllowedFormats. They are all the same. Is it because I checked the tensor output type incorrectly? Let me reiterate my question: engine inference built after modifying the model. Is empty.
from tensorrtx.
Have you check the values of the output tensor for each layer?
I don’t think we should check the Dimensions output by each layer’s tensor. If it is different from the source model, the engine model will not be generated, but I really don’t know what to check. Do you have any ideas? Specifically, we should check which outputs are wrong and lead to inferential reasoning.
from tensorrtx.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
from tensorrtx.
Related Issues (20)
- kernel weights has count 2688 but 32640 was expected HOT 1
- yolov5编译问题 HOT 2
- yolov5s.pt微调后在生成.wts报错,改了数据类别,但类别总数不变。麻烦大大帮忙看看~谢谢!!new.pt是我微调后的模型 HOT 1
- ModuleNotFoundError: No module named 'utils.torch_utils' HOT 2
- 博主你好,这个能部署到windows上面了吗 HOT 6
- win10 compile yolov8 happen:yololayer.cu(262): error : expression must have a constant value HOT 12
- 不使用cmake搭建环境 HOT 21
- yolov8-seg, output error HOT 18
- YOLOV8 Assertion `serialized_engine' failed. 使用自己的.pt 生成 .wts 是成功的,但转.engine 是报错。chat说是卷积层权重数量不匹配 HOT 5
- Unable to build engine file for Yolov7 Custom model HOT 1
- How to use file yolov8_det_trt.py to check one's own model HOT 1
- yolov5-7.0,about anchor HOT 2
- 可以使用onnx模型转换为tensorrt模型,再进行推理吗 HOT 2
- the command : ./yolov5_det -s yolov5s.wts yolov5s.engine s, error!!! HOT 2
- widonws下yolov8模型生成wts转engine文件报错 HOT 2
- ubuntu下yolov5_v5.0的.wts转.engine失败 HOT 1
- 自己数据集训练的yolov9模型tensorrt的输出结果与pytorch结果差别很大,精度完全没有对齐 HOT 8
- 虽然最终得到了engine模型,但是报了这个错误,我是否应该忽视 HOT 1
- yolov8 TRT问题 HOT 4
- There is an error in the reasoning process of yolov8
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.