Jaemin Cho

Hi @minhquan6203 , hmm do you have any ideas on potential cause? maybe something in my dataloader could be fixed

Are there any updates on GQA 2020 @runzeer @airsplay?

Yes, I just found same problems in the raw COCO annotations. Similar problems are in other datasets as well (VG also have similar issue in the second image). Is this...

Hi @zinengtang, thanks for the amazing job! Btw I guess that some files were accidentally added in the vilt model directory (https://github.com/huggingface/transformers/pull/20725/files#diff-5342d82acaa480e404377ccc91a49b5203a3119b02c0dac89bcf147cb32e950e). Could you please check?

+1. This bounding box drawing feature would be very crucial for building demos for many recent layout-guided image generation/editing models. If it's hard to support with current components, then would...

@pkuliyi2015 @gpantaz Sounds good, if you have a public repo, would you please point out the code lines to your implementations?

@rsomani95 's snippet gave me the error below. ```Python TypeError: Expected string index (e.g. 'a'); got 0 ``` In my case, adding `.node` after `joined` solved the problem. ```Python def...

Removing `.node` gave me `TypeError`, regardless of adding `.audio` and `.video` or not. Experiments were done with ffmpeg-python==0.1.18, Python 3.6 in macOS Mohave and Ubuntu 16.04

Thanks for your interest! In our ICCV 2023 version, the previous CLIP-based classification approach is replaced with the BLIP-2 based approach. Please check our [README](https://github.com/j-min/DallEval/blob/main/biases/README.md) for more details.

I don't have enough information to guide this just from the screenshot, but maybe you can first check the generated outputs? Try [colab demo](https://colab.sandbox.google.com/github/j-min/CLIP-Caption-Reward/blob/main/Inference_example.ipynb) and see if your generation results...