-
Hi,
VkFFT says they support zero padding:
"Native zero padding to model open systems (up to 2x faster than simply padding input array with zeros). Can specify the range of sequences filled with ze…
-
This is analogous to this SciPy issue ( https://github.com/scipy/scipy/issues/12228 ). Though it is worth noting that SciPy has done some of the work already ( https://github.com/scipy/scipy/pull/5608…
-
Hi, i've noticed a great speedup when i used lookup based convolutions for training my own network, however the speedup on the inference is quite marginal so i have been wondering if i need to change …
-
Hi Ivan,
Thanks so much for making this package, it's really well-developed. As things stand however, models created using it can't be converted to Torchscript. It may or may not be a problem to so…
-
I think we can produce a significant speedup in our execution of LCA. Since most of the neurons in any LCA computation are below threshold for most of the display period, perhaps we could just ignore…
-
Hello Dr.Cohen, this is another question.
I didn't catch the meaning of GArray and GFuncArray:
A GFuncArray is an array of functions on a group G.
A GArray represents an array that contains…
-
This is the training result in my project. The ```fixup``` is Fixup Initialization (with gradient clipping). The ```renorm``` is Batch Renormalization. The two network both use the same training data …
-
Hello,
I see you've been using boolean masks to mask out the weights of the pytorch network. Is there a way to use sparse tensors to achieve an actual speed up in inference in Pytorch currently ?
…
-
- Zhang L, Agrawala M. [Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543).
- Zhang L. [Ablation Study: Why ControlNets use deep encoder? What if it was…
-
### Model/Pipeline/Scheduler description
TorToise is a multi-voice text-to-speech system, which describes a way to apply recent advances in the image generative domain to speech synthesis. It would…