Ask-Anything
Ask-Anything copied to clipboard
OpenGVLab
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
Hi there! Thank you for the great work. I am trying to train and tune the model on my custom dataset, which has 60-second MP4 video clips and corresponding QA....
Traceback (most recent call last): File "/home/zlj/Ask-Anything/video_chat2/tasks/train_qformer.py", line 13, in from dataset import create_dataset, create_loader, create_sampler, Metaloader ModuleNotFoundError: No module named 'dataset' Traceback (most recent call last): File "/home/zlj/Ask-Anything/video_chat2/tasks/train_qformer.py", line...
I have created a dataset in the following format: - Dataset_folder - videos - video1,mp4 - video2.mp4 train.json train.json is in the following format: [ { "video":"videos/calling.mp4", "QA":[{ "i":"Go through...
How can I use torchrun for single-machine multi-GPU inference testing when running demo.py? I didn't see any usage of DataParallel in demo.py.
where should i download the json files? i mean is this github for developers? if so, why installation document ambiguous?
Hello, As a reference, how long did it take for you to train Stage 1 and 2, respectively (with the training data you described in the paper and set in...
Hello, Thank you for the great work! For stage 4 (instruction tuning with HD data), the current code seems to resize/crop image to 224x224: https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/scripts/videochat_mistral/config_7b_hd_stage4.py#L21 https://github.com/OpenGVLab/Ask-Anything/blob/main/video_chat2/dataset/__init__.py#L73 which means it's actually...
Hi, I'm trying to download the video instruction tuning datasets used in VideoChat2, but the [link for WebVid](https://maxbain.com/webvid-dataset/) is not working. According to the [WebVid repo](https://github.com/m-bain/webvid), they are not supporting...
When I was testing the Mvbench dataset using demo_mistral_hd.ipynb based on mistral, I copied the test code from the mvbench.ipynb file and configured the dataset properly, but it showed such...
