Researcher-DL

Hi, I am interested in running the VQA on a series of images using the model `model_type="vqav2"` as loaded in the[ following code snippet](https://github.com/salesforce/LAVIS/blob/main/lavis/models/pnp_vqa_models/pnp_vqa.py). ``` from lavis.models import load_model_and_preprocess model,...

Hi I was trying to open up colab notebooks to see how models needs to be loaded and how they work. However, all show a window like the following, and...

Hi @xinyu1205 Thanks for the paper, the codes and all the replies here! I have read the issues in embedding but still not sure if RAM++ infernce.py could be used...

Hi there, is there a way to train with a .csv file that has image paths and text descriptions?

Hi, How can I use a pre-trained CLIP-ReID model to evaluate or extract features on a custom dataset when I don't have data to train? I know that I need...

Hi there! I'm interested in total number of found key points within a given image. I was using: ``` %%bash python -m openpifpaf.predict images/peterbourg.jpg \ --checkpoint=shufflenetv2k16-apollo-24 -o images \ --instance-threshold...

[Feature Request]: Reidentification mode

1

### Feature Name FastReID ### Feature Description ### Feature Request: Image Retrieval or ReID Functionality Fastdup's clustering (connected component) already resembles image retrieval. Could you provide details on the method...