import onnxruntime
报错ImportError: Microsoft Visual C++ Redistributable for Visual Studio 2019 not installed on the machine.
onnxruntime
microsoft/onnxruntime: 是一个用于运行各种机器学习模型的开源库。适合对机器学习和深度学习有兴趣的人,特别是在开发和部署机器学习模型时需要处理各种不同框架和算子的人。特点是支持多种机器学习框架和算子,包括 TensorFlow、PyTorch、Caffe 等,具有高性能和广泛的兼容性。
项目地址:https://gitcode.com/gh_mirrors/on/onnxruntime
Traceback (most recent call last):
File “D:/Wanggan_Project/tensorflow/study_test/paddle_steel/file_save_load.py”, line 7, in
import onnxruntime
File “D:\Anaconda3\envs\paddle_new\lib\site-packages\onnxruntime_init_.py”, line 34, in
raise import_capi_exception
File “D:\Anaconda3\envs\paddle_new\lib\site-packages\onnxruntime_init_.py”, line 23, in
from onnxruntime.capi._pybind_state import get_all_providers, get_available_providers, get_device, set_seed,
File “D:\Anaconda3\envs\paddle_new\lib\site-packages\onnxruntime\capi_pybind_state.py”, line 19, in
raise ImportError(
ImportError: Microsoft Visual C++ Redistributable for Visual Studio 2019 not installed on the machine.
可以发现是D:\Anaconda3\envs\paddle_new\lib\site-packages\onnxruntime\capi_pybind_state.py中if not os.path.isfile(“C:\Windows\System32\vcruntime140_1.dll”):
缺失C:\Windows\System32\vcruntime140_1.dll,补全即可
下载链接https://www.66rjz.com/pcsoft/142483.html#download
microsoft/onnxruntime: 是一个用于运行各种机器学习模型的开源库。适合对机器学习和深度学习有兴趣的人,特别是在开发和部署机器学习模型时需要处理各种不同框架和算子的人。特点是支持多种机器学习框架和算子,包括 TensorFlow、PyTorch、Caffe 等,具有高性能和广泛的兼容性。
最近提交(Master分支:7 个月前 )
89f8206b
There is an issue with the 0.46.0 `wheel` version as reported in
https://github.com/pypa/wheel/issues/660. We are currently seeing this
on the Python packaging pipelines, for example in [this
run](https://aiinfra.visualstudio.com/Lotus/_build/results?buildId=740997&view=logs&j=4864752d-f1c3-57c0-06eb-25cee39385a7&s=3fc0883b-27ef-5aa3-1052-0a269c26624c&t=fa95d49e-17f6-501e-c36c-b2949c11fc4a&l=13). 9 小时前
cda0d14c
### Description
This PR is one of a series of changes for optimization of Dawn API
usage. See https://github.com/microsoft/onnxruntime/pull/24281
Optimize the code for workgroup dispatch in the `WebGpuContext` class.
The updated code prefers using the C-API instead of the C++ API for
WebGPU. This is because the C++ API uses class `wgpu::Buffer`, which
causes significant amount of calls to `wgpuBufferAddRef` and
`wgpuBufferRelease` to ensure the lifecycle of the buffer is managed
correctly. For this specific use case in ONNX Runtime (launch a compute
shader program), using the C-API is more efficient. 19 小时前
所有评论(0)