-
Related to #470, I have been wondering if we should make the convergence handling consistent and reusable across methods. Currently, methods handle convergence checks in slightly different ways—some h…
-
`pad` is [implemented](https://chromium-review.googlesource.com/c/chromium/src/+/5727184) on CoreML backend but with lots of constraints.
On CoreML (See [doc](https://apple.github.io/coremltools/sour…
-
Hi, I'm trying to run this example: Tensor-cell2cell-PBMC.ipynb
with c2c.__version__ = '0.7.3'
But at this step:
fig, error = tensor.elbow_rank_selection(upper_rank=25,
…
-
According to the elu definition of [wikipedia](https://en.wikipedia.org/wiki/Rectifier_(neural_networks)#ELU) and the [paper](https://arxiv.org/pdf/1511.07289.pdf), the alpha should be positive.
Th…
-
I'm working on a project where I need to map FX node names to their corresponding ONNX node names, particularly after exporting an FX `GraphModule` to ONNX. The naive approach I've been using involves…
-
In addition to SGD and EM, we should support spectral learning methods. See for example,
> Anandkumar, Animashree, et al. "Tensor decompositions for learning latent variable models." Journal of machi…
-
To integrate various specialized processors such as Tensor Processing Units (TPUs), Language Processing Units (LPUs), Graphics Processing Units (GPUs), and others into the Cyclops-64 architecture, we …
-
Thank you for your great contribution.
I noticed that the dense layer could be incorporated in VGG successfully, but I did not found the implementation of CONV layer, I would like to know if the CON…
-
I have developed the following tensor operation subroutine. Please let me know if there is a need from the community for this tensor operation. If yes, I can merge this subroutine into the develop…
-
### 🐛 Describe the bug
```FlopCounterMode``` reports 0 FLOPS when the forward propagation has the inference mode enabled by ```torch.inference_mode()```. The counter works fine if I use ```torch_no_g…