-
Hi all,
Thank you for this fantastic project and repository! I'm currently working with the REPL example to create an OpenVLA demo/walkthrough and wanted to suggest a couple of improvements:
Sep…
-
`from oml.datasets.base import X` -> `from oml.datasets import X`
So, make all the functions and classes accessible with no more than two-level imports
-
I tried
```
#stage0:
python main.py data/tensoir_syn/tensoir_train/tensoir_lego --workspace ir_lego/ -O --bound 1 --scale 0.8 --dt_gamma 0 --stage 0 --lambda_tv 1e-8 --iters 50000
```
it ret…
-
I am attempting to use gradient accumulation during training to address CUDA out of memory issues. I referred to the example code in the Accelerate documentation as well as the example code in the A…
-
Hi!
Thanks for your great work and a great library to build on top of!
Have you guys considered support for other base LLMs? An example addition (say for a smaller base LLM like Phi 2 or Gemma) mi…
-
Hi,
Thank you for the great open-source work.
However, I am currently facing some difficulties in **reproducing the evaluation results**, particularly regarding the **scene classification on NYU-D…
-
## training problem:
1. 我使用Visdrone数据集进行训练遇到了问题，在执行
```
python tools/train_net.py --config-file ./configs/Visdrone/sbs_R50-ibn.yml MODEL.DEVICE "cuda:0"
```
之后并没有产生报错但也没有进行到iteration中进行训练。
2. …
-
Hello and thank you very much for your project!
I want to fine-tune the pre-trained SpeechT5 model to the ASR task with LibriSpeech data (after that I plan to fine-tune it on some other data). The fi…
-
Movie playback is an event command that uses DirectShow to show a video.
Really awful to support because any format can be thrown at us here...
#### Name of the game:
Any with Video event
#### K…
-
# 🐛 Bug
It is not clear that this is a bug but I am not getting the expected behaviour, consequently, it has been filed under 'bug' but maybe something else.
There are three GPs involved in this…