peterwang512 / gendataattribution Goto Github PK

Hi, thanks for your amazing job! Your findings and methodologies have greatly impressed me and my team and your codes are well organized and really easy to read and understand. We are following your work now. We would like to know whether it's possible to access to the training set?

Thank you for your time !

Hi,

I really liked your work!!!
Do you have any plans for releasing training code ?

Thanks,
Kartik

Hi guys,

Thanks for sharing your amazing project!

I am trying to download the testset images using the provided command:

Download the testset portion of images synthesized from Custom Diffusion
bash dataset/download_dataset.sh testset

However, once reaching ~55GB the download process stops resulting in an error ("file wasn't available on site").
In addition, trying to download directly from the Google drive link
(https://drive.google.com/uc?id=1z7wDJLvBGoW77ijh9HZQPZ9w7tfViCm-)
resulted with the same error.

It worth mentioning that the download of all other dataset and model's weight was successful.

Can you please check the download link again and resolve this issue?

Best regards,
Omer

Hi author,

Thanks for your wonderful work!

I have downloaded the mapper weights from here, and I found that there is only one weight file for each image encoder. I would like to sincerely ask, does this weight file represent the "Object+Style" model in the paper?

If so, would you release the "Object-Centric" and "Artist-Style" models in the near future? I'm very interested in performance comparisons between models fine-tuned on different sets (e.g., DINO Object-Centric outperforms DINO Object + Style on style Recall@10 as shown in Figure 5 in the paper, which is a bit counterintuitive).

Thanks again for your contribution to the community! Looking forward to your reply.