-
The goal of this refactor is to remove all static shape inference within the `onnx-ir` module and focus solely on rank inference. This shift aims to:
1. **Simplify the Shape Inference Process**:
…
-
The ONNX Runtime is missing support for certain data types in some operations. This is currently handled in NDOnnx by casting the operand to a supported type before and casting back after the operatio…
-
### Describe the issue
[DML EP] ORT would crash after deleting one of the models and then doing an inference
### To reproduce
1. Load multi-models.
2. Delete the last model we load.
3. Do an Infere…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### Ultralytics YOLO Component
Pred…
-
### Describe the issue
Onnx Web Inference.
Python + Onnx Inference.
…
-
### Describe the issue
### Description:
I am observing high memory spikes after each run of the inference session when passing the previous outputs of the inference to the input of another iteration …
-
### Describe the feature request
I am trying to use ONNX Runtime in inferencing where preision is very important.
We are training the model in pytorch and saving the weights in double. And exporti…