where is requirements.txt

[emptykk]

1. Clone Repositories and Related Packages
   1.1 image-textualization
   git clone https://github.com/sterzhang/image-textualization.git
   cd image-textualization
   conda create --name image-textualization python=3.8 -y
   conda activate image-textualization
   pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
   pip install -r requirements.txt

[sterzhang]

1. Clone Repositories and Related Packages
   1.1 image-textualization
   git clone https://github.com/sterzhang/image-textualization.git
   cd image-textualization
   conda create --name image-textualization python=3.8 -y
   conda activate image-textualization
   pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
   pip install -r requirements.txt

Hi, thank you for your interest! Actually you can just skip this part, we just use the requirements of the vision experts we use (Groundingdino, detectron2, GRiT, SAM), you can install the corresponding packages of their repos. For the recaptioning phrase, you can just install packages according to LLama3.