Skip to content

Issues: openai/CLIP

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

Clear current search query, filters, and sorts
228 Open 189 Closed
228 Open 189 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

Code for Bias experiments?
#96 opened Apr 21, 2021 by Rijgersberg
"None" gradients when using fine-tuned CLIP
#163 opened Oct 27, 2021 by sarahESL
Different accuracy for different batch sizes
#193 opened Dec 6, 2021 by harryfin
Question about the paper.
#195 opened Dec 15, 2021 by zhhao1
Torch TensortRT
#197 opened Dec 16, 2021 by hfawaz
add ViT-H/16 checkpoint
#229 opened Apr 7, 2022 by dribnet
I failed to convert the ckpt of the clip text encoder in "pytorch" to a "tensorflow 1.15 pb file".
#236 opened Apr 24, 2022 by username123062
Question
#240 opened May 3, 2022 by karmelyoei
Linear probe dataset
#245 opened May 16, 2022 by huangjy-pku
[Question] Performance gap on zero-shot prediction with ILSVRC2012
#246 opened May 20, 2022 by kuri-leo
About the text prompt of OCR dataset IIIT5K-1k
#256 opened Jun 23, 2022 by JingyeChen
How do I use model.encode_image() function in Onnx to get output instead of using default model.forward() function
#263 opened Jul 2, 2022 by deshwalmahesh
YFC100M dataset : Seems to be unavailable
#264 opened Jul 4, 2022 by SachinG007
YouTube video walk-through of this codebase
#265 opened Jul 11, 2022 by gordicaleksa
ImageNet evaluation with linear-probe - logistic regression's C parameter
#277 opened Jul 29, 2022 by IdoGalil
Question: Do the input tokens have to come from clip.tokenize(str) when using the pretrained model?
#279 opened Aug 10, 2022 by sunnypurewal
Result is inconsistent with GPU
#283 opened Aug 26, 2022 by henrywoo
Do the text encoders vary between different clip models
#297 opened Oct 29, 2022 by xiaotingxuan
Testing CLIP VIT robustness
#298 opened Oct 31, 2022 by pbonazzi
Mis-orderred prompt for KITTI dataset
#300 opened Nov 10, 2022 by haooooooqi
model about imagenet-1k
#304 opened Dec 2, 2022 by futureisatyourhand
imagenet-21k class name
#309 opened Jan 3, 2023 by amandaluof
what format were the images used for training?
#320 opened Feb 4, 2023 by jn2clark
Question about simple_tokenizer.
#322 opened Feb 17, 2023 by Mypathissional
visual feature translation question
#328 opened Feb 21, 2023 by wuyou111
ProTip! Type g i on any issue or pull request to go back to the issue listing page.