-
Currently, for ONNX, we are mapping a `U4` datatype (an unsigned 32-bit integer) to an `Int64`.
Should we be instead mapping the `U4` datatype to `Uint32` in ONNX? Or is there no support for a `Uin…
-
Crash was observed on Windows system WinML processing [Windows 10.0.19045]
Callstack is pointing to the following:
```
DirectML.dll!DmlCommandRecorder::ValidateRecordDispatch(struct ID3D12Com…
-
Running tensorflow-directml and now pytorch-directml has possible use with heterogeneous multi GPU training, especially under Linux in WSL2, but the fact that wsl2 docker, wsl2 Ubuntu, and anything re…
-
### Describe the issue
After compilation completed, I only found python whl and C# nuget package, but I canot found c++ library just like:
- install dir
-- bin
-- include
-- lib
### Urgency
…
-
### Describe the issue
When trying to create a session with `onnx_sess = InferenceSession(model, providers=["CUDAExecutionProvider"])` with the dll cudnn_ops_infer64_8.dll missing from the path (o…
-
Hi,
I`ve converted the model using that code:
```
from winmltools.utils import convert_float_to_float16
from winmltools.utils import load_model, save_model
import struct
onnx_model = load_model(…
-
@cynthia in [his talk](https://www.w3.org/2020/06/machine-learning-workshop/talks/machine_learning_in_web_architecture.html?) points out the lack of consensus on a particular format for ML models:
> …
-
### Describe the issue
Hello,
I'm attempting to register a custom operator for the DmlExectionProvider, and getting a crash from `GraphPartitioner.cpp`.
The message is: `Assertion failed: creat…
-
Hi,
I am unable to build onnxruntime with "--build_wheel" and "--enable_pybind" options. I have confirmed that I have python 3.8 installed and all the dependencies. It compiles perfectly without t…
-
## I'm submitting a…
Bug report (I searched for similar issues and did not find one)
The Run command doesn't work , and Save model as well , **`when trying to download Python in Convert tab`** …