search

lyuchenyang / Macaw-LLM

Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration
Apache License 2.0
1.56k stars 127 forks source link

missing file ”data/all_visual_names.json“ #3

Closed wanghao-cst closed 1 year ago

wanghao-cst commented 1 year ago

hi, thank you for making such great work open source. However, I have encountered some issues:

  1. When I run inference.sh, there is a file missing error on 'data/all_visual_names.json', how can I get this file?
  2. Is there trained models we can do inference directly? image
lyuchenyang commented 1 year ago

Hi, thanks for your interests in our work. Regarding your questions:

  1. Please follow the steps in data preprocessing part: python preprocess_data_supervised.py to generate all_visual_names.json and other necessary datasets.
  2. We will release the model weights as soon as possible, stay tuned for more updates!

Thanks

saransh03sharma commented 6 months ago

hi, thank you for making such great work open source. However, I have encountered some issues:

  1. When I run inference.sh, there is a file missing error on 'data/all_visual_names.json', how can I get this file?
  2. Is there trained models we can do inference directly?
image

did you get to know how to use pre-trained model for inferencing purpose only?