Comments (9)
RKNN不支持NMS,需要你把Picodet的输出裁剪到NMS之前
from paddle2onnx.
我是 paddle2onnx 时出错,不是onnx转rknn时出错
from paddle2onnx.
(my_paddlex210_onnx) C:\Users\lenovo>paddle2onnx --model_dir H:\paddlex_workspace\P0025-T0128_export_model\inference_model\inference_model --model_filename H:\paddlex_workspace\P0025-T0128_export_model\inference_model\inference_model\model.pdmodel --params_filename H:\paddlex_workspace\P0025-T0128_export_model\inference_model\inference_model\model.pdiparams --save_file H:\paddlex_workspace\P0025-T0128_export_model\inference_model\inference_model\picodet.onnx --enable_dev_version True
[Paddle2ONNX] Start to parse PaddlePaddle model...
[Paddle2ONNX] Model file path: H:\paddlex_workspace\P0025-T0128_export_model\inference_model\inference_model\model.pdmodel
[Paddle2ONNX] Paramters file path: H:\paddlex_workspace\P0025-T0128_export_model\inference_model\inference_model\model.pdiparams
[Paddle2ONNX] Start to parsing Paddle model...
[Paddle2ONNX] LodTensorArray is not supported.
[Paddle2ONNX] Oops, there are some operators not supported yet, including conditional_block,lod_array_length,select_input,tensor_array_to_tensor,while,write_to_array,
[ERROR] Due to the unsupported operators, the conversion is aborted.
from paddle2onnx.
- 1 PaddleDetection导出模型时设置nms=true
- 2 固定Picodet模型的输入shape测试一下
- 3 详细查看FastDeploy PaddleDetection RKNPU2模型转换教程
from paddle2onnx.
from paddle2onnx.
您好!可是我是 paddle2onnx 时出错,不是onnx转rknn时出错
这是很简单的道理:如果你的模型转换的终点是RKNN模型,那么在RKNN不支持NMS的情况下,你的ONNX模型即使带了NMS有什么意义呢?最简单的办法就是直接在Paddle模型层面裁剪掉NMS及其后面的算子,降低出错的概率。其次,我不明白你这边为什么有这么多不支持的算子,因为我之前测试过PaddleDetetcion2.5是可以直接导出的,即使带了NMS,是不是PaddleDetection版本太低了?
from paddle2onnx.
from paddle2onnx.
那这个需要你问一下PaddleX那边为啥用旧版本的PaddleDetection了,现在Paddle2ONNX应该没有人力来适配旧版本的算子了。
from paddle2onnx.
from paddle2onnx.
Related Issues (20)
- paddle2onnx 在尝试将 PaddlePaddle 模型转换为 ONNX 格式时遇到了不支持的算子(operators):distribute_fpn_proposals 和 generate_proposals_v2。由于这些算子在 ONNX 规范中没有直接的等价实现或者paddle2onnx转换工具中尚未实现对这些算子的支持,转换过程被中止了 HOT 1
- Matting模型转换为ONNX时报错 [pool2d: pool2d_10.tmp_0] While Attribute(ksize)'s type is Tensor, it's not supported. HOT 2
- 【开源之夏】飞桨PaddlePaddle-PIR适配Paddle2ONNX推理转换 HOT 2
- [Discussion] 请求提供 Paddle2ONNX 开发者培训计划 HOT 8
- 转换paddlespeech的KWS部署模型出现了问题
- 无法通过pip install paddle2onnx安装,同时也无法通过编译安装 HOT 6
- paddleseg模型和onnx模型的推理结果不一致,精度差距较大 HOT 2
- [Bug] 关于本地编译安装和执行单测的问题记录 HOT 4
- can't run paddleocr converted model on onnxruntime HOT 3
- unsupported operator: unfold HOT 4
- [Build] abseil demands C++14 or better HOT 4
- 将apollo-model-centerpoint训练的模型转onnx时,报算子不支持的问题 HOT 1
- custom_ops映射使用问题 HOT 2
- unsupported ops: conditional_block,select_input,tril_triu HOT 1
- 量化paddle模型后通过Paddle2Onnx导出onnx存在的问题 HOT 29
- 能否指定 IR representation的版本 HOT 18
- 量化的飞桨模型部署正常,但是转化为onnx模型出现问题(非量化的模型转为onnx可以正常部署) HOT 3
- 编译Paddle2ONNX出现报错 HOT 2
- 请问如何将onnx的输入的batch size 固定为1,现在是动态输入的batch size HOT 1
- Paddle2ONNX New and Upgraded Plan HOT 13
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.