abhidipbhattacharyya

Hi, Could you share the mapping from class id to class label for Faster R-CNN?

Hi, Are you able to get the model? I am also trying to have the pre-trained caption model. I can not download the feature files for flickr30k. The link seems...

@Ammexm I think you can download the models from here https://github.com/microsoft/Oscar/blob/master/VinVL_MODEL_ZOO.md#Image-Captioning-on-COCO

@Ammexm I have not checked that yet but that is my best guess. I am still coding to make it work on my data. If you have already checked please...

Hi, Do you know the format of the TSV files? Can you redirect me to the python files processing this TSV files?

I am able to install apex with torch 1.2.0 and cuda 10.0. I had to use old commit of apex. Here are my commands- git clone https://github.com/NVIDIA/apex.git git checkout 15648029e9d44dccba981e4f07846b3acd799393...

Hi, Where can I find list of all object tags used in OSCAR? I am assuming OSCAR+ uses same dictionary given with VinVL. But I am not sure about the...

> Thanks @klueska @AlexMikhalev both of you. > I had to create preference for nvidia-docker. > > vi /etc/apt/preferences.d/nvidia-docker-pin-1002 > with content; > Package: * > Pin: origin nvidia.github.io >...

For me the following worked- vi /etc/apt/preferences.d/nvidia-docker-pin-1002 I added the content- Package: * Pin: origin nvidia.github.io Pin-Priority: 1002 then I ran- sudo apt-get install -y nvidia-docker2 sudo systemctl restart docker

> Hello, so from what I've gathered using this repo so far, FlanT5 models expect a text_input and a text_output unlike the OPT models for blip2 which just expect image...