-
hi
I have looked at the model and it is a really powerful model
But the problem is in merging the models together, this consumes a lot of gpu power.
If it is possible to separate the models fro…
-
Is there any lora tuning work for this work( [video2video](https://github.com/modelscope/modelscope/tree/master/modelscope/models/multi_modal/video_to_video))?
-
-
In order to be able to contribute the [EgoSchema](https://arxiv.org/abs/2308.09126) benchmark, Inspect has to support video content as input as well as video-LLM models e.g. [VideoLlama2](https://arxi…
-
The HowTo100M + VidChapters-7M + ViTT model is performing poorly on dense video captioning.
Reproduction:
Run
```
yt-dlp -P $TRANSFORMERS_CACHE -o video.mp4 https://www.youtube.com/watch?v=WJ…
-
Thank you for sharing your demo on video moment retrieval models.
As many conferences go on, video moment retrieval models are updated and will be done.
Therefore, do you have any intention or p…
-
If you could also add vision/video transformer models, please. Thanks in advance
-
### Verified issue
- [X] Someone from the team allowed me to create an issue here
### Issue Content
Hi Everyone,
Thanks for your interest in LearnHouse, this is a good first issue for anyon…
-
+ PARTITION=priority
+ JOB_NAME=psg
+ CONFIG=configs/mask2former_vps/mask2former_video_r50.py
+ WORK_DIR=checkpoints/mask2former_r50_vps
+ PORT=1111
+ GPUS_PER_NODE=1
+ CPUS_PER_TASK=1
+ PY_ARG…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…