Yonatan Bitton

@LiJunnan1992 pinging to see if you have an idea about this issue 🙏 🙌

@LiJunnan1992 sorry for the late response, but I also can't reproduce your results based on this information. Is there any chance to provide your implementation first to reproduce the results...

> @yonatanbitton @shengyi4 You can now finetune for retrieval by running this script: https://github.com/salesforce/LAVIS/blob/main/run_scripts/blip2/train/train_retrieval_coco.sh Thank you very much, I am checking that

Update: Downgrading torch to 1.4.0 seems to solve the problem in 2b). However, i'm afraid that after pre-training I'll still have the same problem as 1), meaning that the model...

Thank you for the answer :-) Regarding the FPS: I’d like to understand the relation between ‘Total Time’ and ‘FPS’ described in the tables [here](https://github.com/tucan9389/PoseEstimation-CoreML#total-time-ms). Taking cpm/11-pro as an example,...

@zhangce thanks for the response. Perhaps the answer lies in parsed vs. raw HTMLs? I tried to run the model on un-parsed HTMLs from Wikipedia on CommonCrawl, and now the...

I receive the same error. Was someone able to fix it? @lucidrains ```python line 882, in forward assert len(filtered_data_with_api_calls) > 0, 'your model failed to follow instructions and make API...

Hi, yes it's a limitation of the BLIP2 variant, we plan to work on data release & the end-to-end model, but it will take time. We will update. Thanks.

Hi, we will publish it soon, working on data release. We will update. Thank you :)

Hi, it's updated now in the project website, sorry for the delay, please ask if anything is unclear CSV: https://seetrue.s3.amazonaws.com/wysiwyr_train.csv Images: https://drive.google.com/file/d/1M1CKmYkIdpFYjCOc9JwXHP5Z7E91CJl3/view?usp=drive_link