-
Hi,
Let us assume that we have two triangles connected to make a quad.
I use gltf-sdk to export the quad with 4 UV texture coordinates, one per vertex, as follows.
The upper triangle (T1) h…
-
### 🚀 The feature, motivation and pitch
In graph processing and learning, a famous concept is the **Gather, Apply, Scatter (GAS)** model that utilizes three conceptual phases:
1. **gather**: In …
-
In general, we want to compare two models (e.g. trained with different architectures, loss functions, etc) in multiple different ways:
1. "Macro": comparison of _average_ performance on the entire …
-
I've been scanning ebuilds and source code for packages that use Cuda, and noticed that a lot of them have CMake modules that detect the version of Cuda they use and then use that info to compile the …
-
### Suggestion Description
Dear Tensile Team,
I am reaching out to advocate for the structuring of code in the RocM ecosystem in alignment with Linux packaging conventions. This initiative is no…
-
### 🚀 The feature, motivation and pitch
I'm coding on protein generative task. when data is 6w + function description, the time cost is
 it would be nice to be able to add a thickness to the stroke.
On rectangles and ellipses an option to have the stroke be eith…
-
### Describe the issue
I have a model that is 4137 MB as a .onnx, exported from a PyTorch's `ScriptModule` through `torch.onnx.export`.
When loading the ONNX model through an InferenceSession us…