kasteric

Hi, I encounter a problem when modifying the ssl method of BYOL. Assume there comes a batch of 256 images in the forward function, I want to also include the...

I am wondering whether you use lmdb file or npy file of imagenet-10 to speed up the I/O during training

cannot render obj+mtl+jpg mesh objects with correct textures

2

**System:** - OS version: 22.04 - Python version: 3.11.4 - SAPIEN version: 2.2.2 - Environment: Desktop **Describe the bug** When using sapien.renderer() to render urdf objects from ShapeNet, for some...

About the inference speed of using FullGrad for cam visualization

1

I was using FullGrad for cam visualization and found that it was much slower compared with ScoreCAM or GradCAM, and when using FullGrad for visualizations, there were warnings like `Warning:...

why not a tutorial to transform code base mmdet 2.0 to mmdet 3.0??? Lots of incompatible issues!!

1

**Describe the feature** **Motivation** A clear and concise description of the motivation of the feature. Ex1. It is inconvenient when \[....\]. Ex2. There is a recent paper \[....\], which is...

### Motivation Looking forward to any solution to deploy hornet-L on tensorrt！https://github.com/raoyongming/HorNet ### Related resources https://github.com/raoyongming/HorNet ### Additional context _No response_

custom_hooks = [ dict( type='ExpMomentumEMAHook', momentum=0.0001, priority=49),] Why did you set EMA only for ViT-L, rather than SwinL?

2025-08-07 22:38:53,659] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 2235248 closing signal SIGTERM [2025-08-07 22:38:53,659] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 2235250 closing signal SIGTERM [2025-08-07 22:38:53,661] torch.distributed.elastic.multiprocessing.api: [WARNING] Sending process 2235251 closing signal SIGTERM...