Stack Overflow
Stack Overflow

Questions tagged [onnxruntime]

ONNX Runtime is a cross-platform inference and training machine-learning accelerator.

See onnxruntime github project.

292 questions
0
votes
1 answer

How to include an external file on Android using C# and Godot?

I am trying to export a Godot game to Android using C#. I am using external libraries, like onnxruntime and everything seems to work except for the fact that I cannot include custom files to the exported package. I have already tried to include…
J. Fenigan
  • 119
  • 2
  • 9
0
votes
0 answers

how to use onnx runtime in a custom jupyter ipywidget

I try to use onnx runtime in a custom ipywidget but i have a problem with the *wasm files needed by the wasm backend. I start from the template made by cookie cutter ts and then add the onnx example code provided by onnx : So here my widget.ts code…
nallezard
  • 1
0
votes
1 answer

Why do my ONNXRuntime Inference crash on GPU without any log?

I am trying to run a ONNX model in C# created with pytorch in Python for image segmentation. Everything works fine when I run it on CPU but when I try to use the GPU my application crash when trying to run the inference. (Everything works fine when…
Léo
  • 53
  • 1
  • 8
0
votes
1 answer

Unable to import onnx in Java

I haven't worked with Java much, and I need to load a model trained in Python and check if I can make inference in Java or not. I am trying to load an onnx file in Java. To do this I am importing onnx in Java, but it's throwing an error that package…
Kaushal
  • 1
  • 4
0
votes
0 answers

Improving Inference for BigBirdForSequenceClassification

Any pointers on how to improve Inference for BigBird finetuned on Multiclass Classification? Inference is done on 16GB GPU(NVIDIA). I have already tried Deepspeed and ONNX. ONNX Runtime is not supported for Bigbird and Deepspeed Zero Stage 3 doesn't…
Salman Baqri
  • 99
  • 3
  • 15
0
votes
0 answers

Onnxruntime conversion error from Pytorch model to onnx

I have the follow code to convert from pytorch model to onnx. #Function to Convert to ONNX import argparse import io import numpy as np from torch import nn import torch.utils.model_zoo as model_zoo import torch.onnx from torchvision import…
batuman
  • 7,066
  • 26
  • 107
  • 229
0
votes
0 answers

ONNX Runtime and CWaitCursor on Windows

I'm running a lengthy algorithm on Windows 10, written in MS Visual C++. A portion of the algorithm is inferencing an ONNX model using ORT. I want to spin the wait cursor so the user knows the algorithm is running and not done yet. It spins…
Tullhead
  • 565
  • 2
  • 7
  • 17
0
votes
1 answer

ONNX Runtime memory arena, reuse, and pattern

As described in Python API Doc, there are some params in onnxruntime session options coressponding to memory configurations such as: enable_cpu_mem_arena enable_mem_usage enable_mem_pattern There are some descriptions for them but I can not…
Mohsen Mahmoodzadeh
  • 111
  • 1
  • 10
0
votes
1 answer

onnx runtime without ML.NET

I am trying to run an ONNX inference session in c# in a system that can only run .net framework 4.8.Unfortunetely,framework 4.8 can not run ML.NET and upgrading is not an option. Are there any tricks or workaround that I can get ONNX runtime to…
user101464
  • 35
  • 7
0
votes
2 answers

Using a package from packages.config in C++ visual studio 2017

I am developing a code in C++ using as IDEE Visual Studio 2017 on my Windows 10 workstation. I need the onnxruntime library, so I have installed it by the NuGet package menager. The installation went ok and in my solution I have a folder Resource…
Jonny_92
  • 42
  • 9
0
votes
0 answers

Why does this conversion of an onnx model to tensorflow using onnx-tf fail?

I am working on converting an existing Pytorch model into a tf-lite model to see if it can speed up inference time and make it easier to deploy to mobile. Planned steps: convert pytorch to onnx using torch.onnx.export(). convert the onnx model to…
user1884325
  • 2,530
  • 1
  • 30
  • 49
0
votes
1 answer

ONNX Runtime: Can same ONNX model be inferenced in both a 32-bit App and a 64-bit App?

An ONNX model was supplied to me. I wrote code to inference it via a C++ 64-bit (x64) test program. Works great. But I also need this same model to run in a C++ 32-bit (x86) program -- cannot get it to run there! I can 'load' the model, I can…
Tullhead
  • 565
  • 2
  • 7
  • 17
0
votes
0 answers

'NoneType' object has no attribute 'shape' when using convert_sparkml function and FloatTensorType from onnxmltools library

I searched a lot for my problem but to no avail. This is the runtime version I have on my Databricks cluster: 10.4 LTS ML (includes Apache Spark 3.2.1, Scala 2.12) I have this code below: with mlflow.start_run(): rf =…
eLMagnifico
  • 37
  • 7
0
votes
0 answers

Onnxruntime linking on Android x86

I'm building crossplatform shared library with onnxruntime dependency as static library. I have built onnxruntime from official repo. After that I created empty project and linked onnxruntime to it via CMake: add_library(mylib SHARED…
Egor
  • 107
  • 1
  • 8
0
votes
0 answers

How to get class and bounding box coordinates from YOLOv5 onnx predictions?

I'm new in onnx. How I can convert yolov5 to onnx and get bbox? class YOLOv5ONNX: def __init__(self, model_file: str, device: str = "cpu"): providers = [("CPUExecutionProvider")] self.onnx_session =…
Bombex
  • 1
  • 2
1 2 3
…
19 20