Comments (10)
@VictorBebnev We don't have a plan yet, because DeepSpeech is in V2 API and the convertor here only supports Fluid API.
from paddle2onnx.
This isn't converter V2 API to Fluid API?
from paddle2onnx.
No. It only Merge the model config and parameters into one file
for V2 APIs.
from paddle2onnx.
Hm, converter V2 API to Fluid API doesn't exist?
In Fluid plan you have line( 5.1 convert v2 model to fluid model) about it.
from paddle2onnx.
As far as I know, the conversion from V2 to Fluid is not ready yet, and it has nothing to do with the convertor here.
from paddle2onnx.
Tell me please where i can check status of this converter. It is very important for my project.
from paddle2onnx.
Cannot give a detailed schedule yet. But if you really need Fluid APIs, you'd better develop your project based on it from now on. Waiting for the conversion from V2 to Fluid will be full of risks.
from paddle2onnx.
To implement the project, I use the pre-trained model for V2, without it I can not implement the project, there is no data on which it was trained.
from paddle2onnx.
@VictorBebnev Then I suggest you keep using V2 API, and it should be not necessary to convert the V2 model to Fluid.
from paddle2onnx.
Ok, thanks.
from paddle2onnx.
Related Issues (20)
- jetson编译最新版fastdeloy时,下载不到1.0.8rc HOT 1
- paddle2onnx转换为onnx模型后不能在onnxruntime=1.6的版本运行 HOT 2
- Oops, there are some operators not supported yet, including roll HOT 6
- 转onnx模型报错Cannot found attribute beta in op: swish HOT 2
- [Paddle2ONNX] LodTensorArray is not supported.
- python 版本是 3.9.13. pypi 上能看到 paddle2onnx = 1.0.9 为什么 pip 安装是提示最新的是 1.0.6 , pip 已经更新过了. HOT 1
- pip3安装的用不了,编译安装也失败 HOT 1
- Paddledetection 中的yolov5导出为onnx HOT 1
- paddle2tensorrt "Cannot infer squeeze dimensions from a dynamic shape! Please re-export your model with the Squeeze axes input set."
- module 'paddle.fluid.layers' has no attribute 'pad2d' HOT 4
- Picodet模型导出Onnx出错 HOT 9
- 导出onnx可以设置输入输出的名称吗?例如输入的名称为“input”,输出为“output” HOT 2
- 官方模型:ppmatting-hrnet_w18-human_512导出为onnx失败
- PaddleOCRv3量化模型转ONNX推理bug HOT 3
- 需要将Paddle模型转换为onnx,报错:[ERROR] Cannot found attribute beta in op: swish HOT 6
- (已经在issues里找过一圈答案了没有解决)faster_rcnn 转onnx 提示there are some operators not supported yet, including distribute_fpn_proposals,generate_proposals_v2 HOT 1
- ppocrv4识别模型转onnx时,修改输入shape,出现数值偏差很大的问题 HOT 1
- mask-rcnn明明我找到的issue上面显示已经支持generate_proposals_v2算子的转换了,但是我转换的时候还是提示不支持转换的op HOT 1
- Can not set input_shape when converting inference model to onnx
- paddle2onnx转化相关问题 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 paddle2onnx.