openai/CLIP

Issues

• RuntimeError: Input is too long for context length 77. No truncation passed

  #468 opened 3 months ago by hessaAlawwad
  1

• Segmentation Fault On Importing Clip

  #447 opened 7 months ago by AbdelrahmanMohamed129
  1

• Are there public datasets in your WIT dataset ?

  #475 opened 22 days ago by soniamartinot
  0

• colab [8] error：No such file or directory: '/root/.cache/scikit-image/0.24.0/data'

  #474 opened 24 days ago by a-persimmons
  0

• tokenize() got an unexpected keyword argument 'return_length'

  #472 opened 3 months ago by 124578-chj
  1

• out proj weight typo fix

  #473 opened 2 months ago by louiswang524
  0

• welcome to my clip.cpp project, support openai clip and chinese clip model, quantization type(q4,q8_0,f16,f32), metal gpu and cuda speed

  #463 opened 4 months ago by yysu-888
  0

• pip subprocess error

  #471 opened 3 months ago by Uduba-robo
  0

• pip subprocess error

  #470 opened 3 months ago by Uduba-robo
  0

• How do I open clip for other visual tasks？

  #469 opened 3 months ago by kunge98
  0

• I've set the `explorer.autoReveal: false` in my settings.

  #467 opened 3 months ago by Karliz24
  0

• How to subdivide the same category, for example, how to distinguish Persian cats, coffee cats, and jingle cats, which are all cat categories?

  #466 opened 3 months ago by watertianyi
  0

• The provided ImageNet label list has missing/duplicate labels.

  #465 opened 3 months ago by gstoica27
  0

• My CUDA Has seen the GPU but did not use it, why?

  #443 opened 8 months ago by Mark-ssss
  2

• What is the best practice to train image with multiple captions/keywords

  #464 opened 3 months ago by pengzhao-life
  0

• On YouTube channel

  #461 opened 4 months ago by Cascadipalone
  1

• How to convert CLIP vectors to an LLM text token embeddings?

  #460 opened 4 months ago by xoraizw
  0

• Preprocessor - How does it work?

  #459 opened 5 months ago by whishei
  0

• Comenzó

  #457 opened 5 months ago by Karliz24
  0

• Issue with Text Encoder Output Dimensions in Fine-Tuned CLIP Model When Using with Stable Diffusion

  #452 opened 6 months ago by QXGeraldMo
  1

• How to run in

  #455 opened 6 months ago by Izaankaskar
  0

• About rope-vit

  #454 opened 6 months ago by CoinCheung
  0

• Is that normal that logits are not within -1 to 1?

  #444 opened 6 months ago by Leo-T-Zang
  0

• Jupyter Keeps crashing when trying to initialize CLIP

  #448 opened 7 months ago by SSdevelop
  2

• `from pkg_resources import packaging` seems not work with `setuptools>=70.0.0`

  #446 opened 8 months ago by PawelPeczek-Roboflow
  1

• If the text embedding can be recovered to text?

  #428 opened 10 months ago by Zhangwenyao1
  2

• Question about Checkpoint on ResNet-50.

  #445 opened 8 months ago by MorningStarOvO
  0

• How to change the features obtained by the clip encoder[1, 512]

  #441 opened 8 months ago by lwtgithublwt
  0

• Enquiry about the FER2013 dataset used in CLIP paper

  #439 opened 9 months ago by hyy-2000
  0

• CLIP

  #438 opened 9 months ago by DorsaCharkhian
  0

• What data did ori checkpoint that provided by official use?

  #437 opened 9 months ago by SuperGoodGame
  0

• On a Bag-of-Words baseline and a transformer

  #436 opened 9 months ago by iburenko
  0

• from pkg_resources import packaging

  #434 opened 9 months ago by qiuyangyue666
  0

• Did CLIP use COCO for training?

  #433 opened 9 months ago by slavaheroes
  0

• Context Length Error

  #432 opened 9 months ago by hamza13-12
  0

• How to get all the features of the image encoder and text encoder

  #431 opened 10 months ago by wuyukun-tong
  0

• Multi-thread usage of open_clip

  #430 opened 10 months ago by mobines96
  0

• encode_text gives different clip features for the same text, single batch vs mutliple batch

  #429 opened 10 months ago by KevinNWalker
  1

• some confusion about fine-tunning CLIP

  #427 opened 10 months ago by SoulProficiency
  0

• Determine how similar the text I entered is to the text in the training set

  #426 opened a year ago by yumianhuli1
  0

• R50x64.pt SHA256 does not match - fyi

  #425 opened a year ago by xvdp
  0

• How to combine with ControlNet?

  #424 opened a year ago by MinzChan
  0

• about position embedding scale

  #423 opened a year ago by OliverHuang1220
  0

• What is impact on the image embedding result when the alpha channel is dropped by the converter

  #422 opened a year ago by githubusersel
  0

• Mistake in tutor

  #421 opened a year ago by spzhuang
  0

• Dimension Discrepancy in VisionTransformer?

  #420 opened a year ago by Shiran-Yuan
  0

• Please add VIT-G support

  #419 opened a year ago by ppbrown
  0

• RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'

  #415 opened a year ago by Viditagarwal7479
  1

• CLIP Recognition Error

  #416 opened a year ago by nhw649
  2

• Regarding the fact that the clip library can only be used to read data using the PIL library, we hope that the official can modify the source code

  #418 opened a year ago by qsd-github
  0