Ask-Anything
Ask-Anything copied to clipboard
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
Hi, The original code includes the line `models.videochat2_it import VideoChat2_it` to load the model. However, it seems that there is no `videochat2_it.py` file available to import the model configurations. To...
Hello, I am currently studying lots of things on MVBench and was wondering why you provided functions for EgoSchema such as check_answer_egoschema() but not for MVBench? Since MVBench is the...
请问text_input的形式是什么样的,可以举一个例子吗 
由于显卡不是很充足,我将config中的freeze_vit和freeze_qformer都设置成了True,同时添加了freeze_lora,在models/videochat_mistra/videochat2_it_mistral.py中添加 ``` if self.freeze_lora: logger.info("freeze lora") for _, param in self.mistral_model.named_parameters(): param.requires_grad = False self.mistral_model = self.mistral_model.eval() self.mistral_model.train = disabled_train ``` 也就是说,我希望我只训练线性层的参数,然而在训练过程中出现 WARNING | py.warnings : .../anaconda3/envs/videochat2/lib/python3.9/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of...
Thank you for the excellent work! If I want to reproduce your results, I would first need to download the datasets for stage 1, stage 2, and stage 3. However,...
Hello, Thanks for releasing MVBench and all the other great things! I am studying video understanding benchmarks in my research and was wondering if you could release the scripts/prompts for...

It seems that there is an issue with the evaluation method in MVBench. Currently, the process of verifying correctness involves splitting the prediction and extracting only the first segment(word) to...

(videochat2) root@58df28cdb848:/tf/Ask-Anything/video_chat2# python demo/demo.py Traceback (most recent call last): File "/tf/Ask-Anything/video_chat2/demo/demo.py", line 17, in from models.videochat2_it import VideoChat2_it ModuleNotFoundError: No module named 'models.videochat2_it'