Skip to content

Issues: salesforce/LAVIS

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

451 Open 225 Closed
451 Open 225 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

PIP ENV NEVER WORK
#775 opened Dec 13, 2024 by 5e1in
How do I evaluate the results after stage-1 of training BLIP2?
#774 opened Dec 12, 2024 by hawkiyc
RuntimeError: Error(s) in loading state_dict for Blip2OPT: size mismatch for opt_proj.weight: copying a param with shape torch.Size([2560, 768]) from checkpoint, the shape in current model is torch.Size([768, 768]). size mismatch for opt_proj.bias: copying a param with shape torch.Size([2560]) from checkpoint, the shape in current model is torch.Size([768]).
#773 opened Dec 7, 2024 by chilljudaoren
Issue related to BLIP2 CaptionDataset implementation or blip2_qformer.py for custom dataset pre-training stage 1
#772 opened Dec 4, 2024 by abdel-habib
1
RuntimeError: shape mismatch: value tensor of shape [131072] cannot be broadcast to indexing result of shape [0]
#771 opened Dec 4, 2024 by jyh-fort
1
text and image embedding from xgen-mm-phi3-mini-base-r-v1.5
#770 opened Dec 3, 2024 by sangeethkumar1997
blip2_feature_extractor problem?
#769 opened Dec 1, 2024 by wahaha-debug
The odd captions for inputing pure black/white picture to the BLIP model
#768 opened Nov 27, 2024 by FaxinZ
ImportError: numpy.core.multiarray failed to import when trying to use salesforce-lavis in Huggingface app
#767 opened Nov 16, 2024 by jchwenger
OSError: Can't load tokenizer for 'google/flan-t5-xxl'.
#766 opened Nov 11, 2024 by JoycePerm
blip2 feature
#765 opened Nov 7, 2024 by cqray1990
hasattr(dataset[split], "coco_fmt_qust_file"), KeyErrror: "val"
#764 opened Nov 7, 2024 by ArkZero35
A slip of the pen concerning paper URL in README
#763 opened Nov 4, 2024 by whyisverysmart
ImportError: numpy.core.multiarray failed to import
#762 opened Oct 29, 2024 by lvilaca16
10
Can instructBLIP realize context learning? Give some sample pictures and sample descriptions in advance, and then generate descriptions of the same style according to the new pictures? )
#761 opened Oct 26, 2024 by yuanllong
Will blip-diffusion release the training code?
#759 opened Oct 22, 2024 by Hiccupwzy
Question for the meaning of BLIP2 embedding.
#758 opened Oct 16, 2024 by Roberyan
transformers version support
#757 opened Oct 16, 2024 by YeonjeeJung
2
Why blip2_feature_extraction does not align with demo
#756 opened Oct 14, 2024 by Roberyan
Environmental Error
#755 opened Oct 14, 2024 by returnaaa
1
build dependencies did not run successfully because there is no compatible version of numpy
#754 opened Oct 13, 2024 by 7w01
4
Is it possible to use blip-2 model without the LAVIS env?
#752 opened Oct 8, 2024 by Roberyan
Isn't it possible to adapt GradCAM in VQA Models?
#750 opened Sep 25, 2024 by V2LLAIN
How can I provide some examples to BLIP2 and InstructBLIP models?
#748 opened Sep 24, 2024 by xukefaker
1
Multi GPU training is stalling with 100% GPU utilisation.
#747 opened Sep 24, 2024 by SouravMzdr
3
ProTip! Exclude everything labeled bug with -label:bug.