Hot answers tagged

2 votes

How to add a new item in the embeddings vocabulary?

If outright retraining is out of the question (which honestly makes sense since it'd likely be time and resource intensive), then you can try a couple things: Treat this as an out-of-vocabulary ...
rabbit's user avatar
  • 421
1 vote

Performance difference between two equivalent ML codes

The solution to this problem is rather simple: Using different settings for the likelihood noise results in significant changes in the MAE values. Using the same likelihood noise in GPyTorch and ...
C_Swann22's user avatar
  • 111
1 vote

Image segmentations vs image detection

It's an interesting question. I don't think there is a definitive "always true" answer. So empirical results would prevail. To me, the biggest factor regarding accuracy would be the type of ...
Valentin Calomme's user avatar
1 vote

Image segmentations vs image detection

Image Segmentation can extract objects from environments now adays after Meta published SAM (SegmentAnything) and even with few-shot learning can perform very well. Recommend using it to set the stage ...
Emad Ezzeldin's user avatar
1 vote

"'cuda:6')" becomes (nvidia-smi) GPU 4, same with any other "cuda:MY_GPU", only "cuda:0" becomes GPU 0. How do I get rid of this mapping?

You can try setting environment variable CUDA_DEVICE_ORDER to value PCI_BUS_ID to get the ordering to be the same as the ...
noe's user avatar
  • 25.5k
1 vote

Supported GPU for Pytorch

Caveat: haven't tried this myself, but last year AMD announced ROCm 5.7 support for Pytorch on a couple of their graphics cards running Ubuntu: &...
brewmaster321's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible