-
Hi, have you tested the technique mixup (Mixup: Beyond Empirical Risk Minimization) for the different datasets? Is with this technique models can show better performance on dataset IJBC?
-
`moment.locale(opts.lang || opts.language);`
being called before calling the `moment()` function is problematic.
This will force you to use one language throughout your templates, i fixed it in a …
-
```
def (>>>)(f:(a) -> b, g:(b) -> c) -> (a) -> c given (a, b, c) = \x. g(f(x))
```
The parser still has a precedence for the `>>>` operator, so I tried to revive it as above. But when I tried r…
-
When setting up and using multiple `direct-tcpip` channels concurrently there seem to be some kind of bug where the the different channels end up being confused and the wrong one used.
## Reproduct…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
In a project which is part of internal deployment running 1.12.12, some users noticed a strange thing: for a C file (`fem.c`), the definitions in the file (as reported by the Navigate pane - clicking …
-
multi-output labels are typically dictionaries with Tensor keys. We can iterate over these and blend them.
-
**Describe the bug**
When I download the addon from release page description shows its 2.2.3 but when installed, it shows as 2.2.2.
I hit check for update, and it shows that 2.2.3 is available.
…
-
我看了下lic-mixup的数据，想请问下，感觉lic-mixup应该是Single-hop QA数据集吧
-
Should we use data augmentations/ mixup for finetuning on pseudolabels? I think data augs should be significantly less aggressive for the pseudolabeling. However, do we want that to mean a different s…