-
we have for v1.1: MIVisionX_WinML-installer.msi
-
## I'm submitting a…
Bug report (I searched for similar issues and did not find one)
## Current behavior
I am trying to run a model created by Keras backed by Tensorflow using Window…
-
I'm submitting a…
## Current behavior
I export a trained model from Keras that works perfectly in Keras and TF. I export to onnx 1.2.3 with opset version 7, and i run it in WinMLRunner. It ke…
-
Samples and Apps need to be updated to match the new API's.
-
I'm new to ONNX runtime.
We have several CUDA projects, Open GL usage in our product.
How would they interact with WinML's (ONNX) GPU based inferencing, like process prioritization? For example,…
-
Is it possible to edit name of layer in onnx?
Seems here is only part of the answer, i.e. protobuf to json
https://github.com/onnx/onnxmltools/issues/273
then we can edit json, but how to convert…
-
**Describe the bug**
(performance) ONNX runtime applies an optimization that transforms the graph MatMul + Add -> GEMM for floating point tensors. However, an overly strict type check prevents that s…
-
**Describe the bug**
The Resize operator fails with the following simple 2D test case.
{
"op_type": "Resize",
"mode": "linear",
"X": [[1, 1],
[1, 1]],
…
-
**Describe the bug**
The Lotus CPU implementation OneHot rejects negative axes except -1 (rejects -2, -3...) which is overly strict and inconsistent with the spec. It should treat negative values lik…
-
Why are the scores returned by `output_probability` a list of dictioniaries?
That is different from the sklearn api and much less efiicient for larger datasets.