-
### Discussed in https://github.com/orgs/ultralytics/discussions/14959
Originally posted by **vinycecard** August 5, 2024
I'm training AIs separately, one for each type of identification (e.g…
-
-
The goal is to make sure that a user can use persisted model (saved to disk as binary model or MOJO and loaded back into H2O) as a base model.
* Investigate what information is possibly lost due to …
-
**Is your feature request related to a problem? Please describe.**
There are some workflows that it would be good to run before the run model starts, and some workflows that might clean up after ever…
-
Hi!
Currently we have the functionality to handle pdb files with multiple models in it. It renders a trajectory control panel to navigate between models.
I am looking for a way to achieve th…
-
Hello!
If I have two trainers (say two different losses) -- How would I go about ensembling them for inference?
Basically, get the ensemble of all the folds for each trainer (which usually happens…
-
The following paper by Rich Caruana
http://www.niculescu-mizil.org/papers/shotgun.icml04.revised.rev2.pdf
presents an simple greedy algorithm to stack models.
It is reported by many people to be an e…
-
**Describe the bug**
I am deploying an ensemble of an NLP model. While running the code specified, I get this error:
```
Unable to initialize shared memory key 'triton_python_backend_shm_region_2' …
-
**Description**
A clear and concise description of what the bug is.
We set cache cleaning args on all models running on GPU. After calling them individually repeatedly, the GPU RAM utilization wil…
-
Hey @sjahangard
1) I assume this function is used to draw frames from the video and feed them to the image-based model. Is that correct?
https://github.com/JRDB-dataset/JRDB-Social/blob/b9b5ee…