-
Congratulations on shipping FNA backward! Looking forward to using it.
On another note: would it be possible to support arbitrary masking?
MaskDiT outperformed regular DiT, with a 70% reduction …
-
## 🔨Work Item
**IMPORTANT:**
* This template is only for dev team to track project progress. For feature request or bug report, please use the corresponding issue templates.
* DO NOT create a new…
-
### 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…
-
## Request Overview
Upon briefly looking at the cursed iron masks and the various classes that have them, I decided to make a list of suggestions to add new ways for kings to exercise their authori…
-
Hi,
Llama 3 trains like this
> We trained the models on sequences of 8,192 tokens, using a mask to ensure self-attention does not cross document boundaries.
I see you have something like this…
-
hello!
This is a interesting work! Please, can you tell me how to generate the "OpenImageV6 train_mask.json"?
thank you very much.
-
### Describe the bug
/.conda/lib/python3.10/site-packages/kornia/augmentation/_2d/mix/base.py", line 124, in apply_non_transform_mask
raise NotImplementedError
NotImplementedError
### Repr…
-
Hallo
How can I use
nonlinear constraints with boolean masks in AX?
-
![1720147935352](https://github.com/PaddlePaddle/PaddleOCR/assets/43359721/41d332ec-1315-4a71-b594-4508d704b1f3)
报错代码:
class DiceLoss(nn.Layer):
def __init__(self, eps=1e-6):
super(D…
-
If it is a multi label mask and there are multiple masks when converting to one hot, how can data be stored in the labelTr folder?