-
### Describe the issue
ONNX opset version: 14
When 2 duplicate nodes(which have the same inputs and outputs) of torch.Tensor.to are defined, the model produce wrong results after ort optimization.…
Azyka updated
10 months ago
-
Hi, thank you very much for providing the code. I'd like to ask on what hardware configuration this model was trained, how long it took to train, and if I want to run this code, how should I adjust th…
-
This is an awesome project and I hope it will mature even more together with julia's growth! Thanks for having realized the state it is now.
# Some Introductory Words
I like to contribute in the long…
-
Hi,
Is it possible to plot graphs of the various stats (`expected_improvement`, `predicted_value`, `success_probability`, etc.) under the hood when using the `bayes` method to do an hparam sweep wi…
-
The above instruction `pip install multi-vector-simulator[report]` can not install everything on windows that is required for the report. This connects to the necessity to have a `.yml` file (#476).
…
-
We should probably look into the kinds of fusions that turn scalar constants into inputs.
For example,
```python
import aesara
import aesara.tensor as at
x = at.vector("x")
y = at.exp(x …
-
**Why this Mod?**
Graph problems are always nice and the picture for the gallery is already clear :)
The problem is easy to understand and well-known.
**What will the API be?**
It can be don…
-
**Describe the bug**
MergeShape fails and ONNXRuntime returns results in a wrong shape with warnings below:
```
[W:onnxruntime:, graph.cc:106 MergeShapeInfo] Error merging shape info for output.…
-
The downloaded dependencies contain quite a lot of polyfills and unnecessary dependencies.
For example [fs.realpath](https://www.npmjs.com/package/fs.realpath) required only for Node.js@
-
**Timeline**: before MainNet.
**Requirements**:
- [ ] Gas costs communicated clearly in each appropriate channels
- [ ] A builder can estimate how much it's going to cost them to run on NEAR
- […