-
This should implement https://github.com/rust-lang/rust/issues/48750, but for starters just containing the FROM-SCRATCH and SMALL-CHANGE usage scenarios.
I imagine this to be a separate page on per…
-
### 🐛 Describe the bug
To reproduce my issue, run this code:
```
import torch
class Model(torch.nn.Module):
def forward(self, inputs):
xseq = inputs[0].detach().requires_grad_()
…
-
### Is your feature request related to a problem? Please describe.
Face landmark detection is the task of mapping a person's face for better computing and processing by software and machines. These l…
-
As far as I can tell, preconditioning using domain decomposition methods is not something that seems to be supported. Is this something that is within the scope of `Ferrite.jl`? Of course there are C …
-
## 🚀 Feature
Sometimes you want to apply augmentations to e.g. masks the need to transform also an image.
## Alternatives
None
## Additional context
When using AugmentationSequential li…
maaft updated
2 years ago
-
咨询您如果周期边界或者非0边界如何处理fpinn中的分数阶拉普拉斯算子离散。
-
### 🐛 Describe the bug
## nn.CosineSimilarity returns value larger than 1
When I was computing cosine similarity, it returned a tensor([1.0000]). However, it's larger than 1, which leads to the ru…
-
### 🚀 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 …
-
A thorough revision of the "Manual" section of the documentation is needed. There is no transition between the different sections and some important features are only found in the Library (API Referen…
-
Hi,
I would like to use firedrake to do computations on isoparametric meshes in 3D in parallel. I have some code that worked nicely in serial but for parallel I have switch to `par_loop`s.
Howe…