jepa

jepa copied to clipboard

In the READme "Launching evaluations" section there is a typo in the three following scripts: ``` python -m evals.main \ --fname configs/eval/vitl16_in1k.yaml \ --devices cuda:0 cuda:1 cuda:2 ``` ``` python...

atonkamanda

cannot run the v-jepa attentive probe checkpoint for my custom task, Seems to be some issue with the environment .  This error is a numpy import...

tomarvimal

Question: no release of decoder checkpoint?

1

Hi, thanks for the great work. I checked the downloaded checkpoint and find that there is no decoder model checkpoint mentioned in the paper that was used for mapping the...

LumenYoung

Hi there, Congratulations on such a brilliant release. I'm VB, leading the advocacy efforts for open source at Hugging Face. I saw that the model checkpoints are released as CDN...

Vaibhavs10

Cannot access the config file vitl16_k400.yaml

2

When I click on the link to download configs/eval/vitl16_k400.yaml, I came across the following error: 404 - page not found The main branch of jape does not contain the path...

jmgrn61

orena1

Dimensional Collapse Tracking

1

Hello, first of all, thank you for sharing this kind of model. I have a question regarding the development of this model, particularly about the collapse of the dimension. Do...

zankerx

Hello everyone, Thanks for the source code ! Is it possible to adapt V-JEPA to 3D imaging (like medical imaging)? I don't know which aproach would work best between converting...

arnaudberenbaum

is it possible to learn an action model (or the action's effects) with v-jepa ?

3

Hello, I would like to know if it is possible to add the knowledge of the actions performed by an agent into the architecture. From my understanding the unmasked part...

aymeric75

Wip cloud training

1

gothera