Comments (7)
Jiang-Jia-Jun
commented on July 18, 2024
这个问题先前看到反馈过多次。 使用ONNX Runtime CPU应该可以推理，使用ONNX Runtime GPU且关闭图优化也可以推理。 可以自行再测试下，可能得在ONNX Runtime仓库下提问
from paddle2onnx.
diyaxxxx
commented on July 18, 2024
这个问题先前看到反馈过多次。 使用ONNX Runtime CPU应该可以推理，使用ONNX Runtime GPU且关闭图优化也可以推理。 可以自行再测试下，可能得在ONNX Runtime仓库下提问
感谢回复。
onnx在CPU上是可以推理的，目前的需求是在GPU上推理
根据sess_options.graph_optimization_level = rt.GraphOptimizationLevel.ORT_DISABLE_ALL关闭图优化
关闭图优化后，onnx在CPU上推理失败
在GPU上推理失败
from paddle2onnx.
Zheng-Bicheng
commented on July 18, 2024
CPU能推理GPU不能推理看上去像是ONNXRuntime自身的问题呀
from paddle2onnx.
diyaxxxx
commented on July 18, 2024
CPU能推理GPU不能推理看上去像是ONNXRuntime自身的问题呀
换过几个onnxruntime版本都会有相同的错误
from paddle2onnx.
Zheng-Bicheng
commented on July 18, 2024
换过几个onnxruntime版本都会有相同的错误
我的理解是，CPU能推理说明模型本身没问题。至于你说的ONNXRuntime换了几个版本都不行，是不是把模型提交到ONNXRuntime的Issues让他们帮忙看下呢？
from paddle2onnx.
diyaxxxx
commented on July 18, 2024
换过几个onnxruntime版本都会有相同的错误
我的理解是，CPU能推理说明模型本身没问题。至于你说的ONNXRuntime换了几个版本都不行，是不是把模型提交到ONNXRuntime的Issues让他们帮忙看下呢？
好的，谢谢，已经提交了
from paddle2onnx.
diyaxxxx
commented on July 18, 2024
这个问题先前看到反馈过多次。 使用ONNX Runtime CPU应该可以推理，使用ONNX Runtime GPU且关闭图优化也可以推理。 可以自行再测试下，可能得在ONNX Runtime仓库下提问
感谢！问题解决！关闭图优化之后在GPU上推理成功，之前的测试代码不正确，导致仍然报错，测试成功代码如下：
from paddle2onnx.
Related Issues (20)
- UIE多输入转onnx后输入结构与原模型不符 HOT 1
- Paddle OCR 推理模型转ONNX，固定shape后，ONNX结果相差很大，不固定shape，结果与paddle推理模型保持一致 HOT 6
- 当我使用opset 7测试bitwiseand时报错 HOT 2
- pip install failed! HOT 1
- [ERROR] Cannot found attribute output_padding in op: conv2d_transpose HOT 2
- There are some operators not supported yet, including einsum, repeat_interleave HOT 5
- when I choose convert fp16 onnx, My ATC export is wrong
- AttributeError: module 'paddle2onnx' has no attribute 'dygraph2onnx' HOT 1
- 安装paddle2onnx会强制修改numpy版本 HOT 2
- [讨论]关于mapper_registery.h.in 里REGISTER_MAPPER宏的new 操作的疑问 HOT 2
- 在转换模型时遇到了如下错误： Can't parse message of type "paddle2onnx.framework.proto.ProgramDesc" because it is missing required fields: blocks[0].ops[27].attrs[7].type, blocks[3].ops[12].attrs[7].type HOT 1
- 使用X2Paddle将ONNX模型转Paddle时报错 HOT 1
- 【🚀需求🚀】支持控制流conditional_block + select_input 系列算子的支持 HOT 4
- 【🚀需求🚀】支持飞桨 swiglu 算子转ONNX HOT 1
- 【🚀需求🚀】支持飞桨 top_p_sampling 算子转ONNX HOT 1
- paddle2onnx 编译python wheel 包问题 HOT 4
- TypeError: export() got an unexpected keyword argument 'model_file' HOT 1
- paddle ocr 转onnx之后精度损失 HOT 10
- paddleocr:export onnx and inference error
- SLANet-LCNetV2 转onnx模型报错 HOT 6
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 paddle2onnx.