-
I tried running the [evaluation code](https://github.com/PKU-YuanGroup/Video-LLaVA/blob/main/scripts/v1_5/eval/eval_image_llavabench.sh) on [your model checkpoint](https://huggingface.co/LanguageBind/…
-
不好意思 想请教一下 在Data Preparation部分的第三步3. Convert and Crop the Videos 执行python3 tools/video_convert.py --codec=libx264 --keyint=60 --resize=240 -i dataset/msvd/videos -o dataset/msvd/videos_240_h264_keyint…
-
Hi, guys! Thank you for the project a lot. But I have an issue with downloading pretrained models using download_models.sh. I've tied different networks, but it fails all the time. Do you have another…
-
A related issue posted in https://github.com/bytedance/Flash-VStream/issues/2.
After **training the model by myself** following scripts in this official repo, the evaluation results on MSVD and M…
-
--do_eval can get correct zero-shot performance
but --do_train meets NaN at the sta…
-
**Describe the feature**
提供多种损失函数的sft训练，比如对比损失
**Paste any useful information**
sft时，除了交叉熵损失，有时需要针对某个特定token计算对比损失、pairloss等等，可否集成这样一个功能呢？
**Additional context**
-
Hello. Thank you for sharing your interesting research.
I was able to easily reproduce the results of the DiDeMo dataset by demo script (run_didemo.sh). However, when attempting to reproduce the MSR-…
-
Hi, I managed to execute 2 phrases of training without any problems. But evaluation doesnot work, please check the following log. Thank you
```
(DiffusionRet) hai@user:~/sang$ CUDA_VISIBLE_DEVICES…
-
Dear authors,
Great work and thanks for releasing the code for ViClip pretraining on InternVid-10M-FLT. Firstly, It would be really great if the pre-trainning instructions are more detailed, like w…
-
```
PYTHONPATH:
which python: /opt/conda/envs/umt/bin/python
PYTHONPATH: :/opt/conda/envs/umt/bin/python:.
torchrun.sh: line 2: scontrol: command not found
torchrun.sh: line 3: scontrol: command…