SunzeY/AlphaCLIP

Issues

• Does alphaclip have a model version suitable for ViT-H/14?

  #69 opened 2 months ago by ascv0228
  0

• How to improve semantic differences between different objects

  #67 opened 3 months ago by jkff00
  3

• Performance of image level visual language tasks for alpha-clip LLaVA-1.5

  #68 opened 3 months ago by Lay-du
  0

• alpha clip训练

  #65 opened 3 months ago by dox012
  3

• image patch embedding

  #66 opened 3 months ago by frederhoon
  1

• if i want The training input data is four channels, because my six-channel data is spliced ​​from six single-channel 2D images. How should I modify the code? I do not have a mask annotation file. Can I use this code?

  #63 opened 5 months ago by watertianyi
  1

• image default

  #61 opened 8 months ago by Mxhjsz123
  1

• 大佬好

  #62 opened 8 months ago by Mxhjsz123
  0

• How to get target image embeddings for retrieval with AlphaCLIP?

  #59 opened 8 months ago by raghav-akridata
  1

• Guidance needed: Processing GRIT-20M dataset in .parquet format for Alpha-CLIP

  #60 opened 8 months ago by qingpowuwu
  1

• CLI environment demo of "alphaclip with LLM"

  #58 opened 8 months ago by sunwoo76
  0

• Regarding the DataLoader and get_file function Issue

  #57 opened 8 months ago by LinMu7177
  0

• No such file or directory: 'data/imagenet_s/imagenet_919.json'

  #56 opened 8 months ago by LinMu7177
  2

• Some of the code is not publicly available

  #55 opened 8 months ago by eorroot
  2

• Good work! How to get patch embedding of image？

  #54 opened 8 months ago by cyysc1998
  1

• When will release the training code of alpha-CLIP? 忍不住问了。

  #51 opened 8 months ago by LinQianhe02grey
  2

• When do you release the training code?

  #47 opened 8 months ago by oishikimchi97
  1

• Your demo code on HuggingFace is throwing 502 Gateway error

  #49 opened 9 months ago by vbayanag
  7

• UnpicklingError: invalid load key, '<'.

  #44 opened a year ago by bolongliu
  1

• When will release the training code of alpha-CLIP?

  #43 opened a year ago by joeyz0z
  2

• ViT-H/14

  #45 opened a year ago by YigitEkin
  1

• Training Code Release

  #48 opened 9 months ago by Zhiyuan-R
  1

• Data release

  #52 opened 9 months ago by CharlesGong12
  1

• Web Demo 502 Bad Gateway

  #50 opened 9 months ago by CharlesGong12
  2

• Web demo of Alpha-CLIP with Stable Diffusion doesn't work?

  #42 opened a year ago by Haiyan-Chris-Wang
  3

• High Image Cosine Similarity Scores even with completely different images

  #46 opened 10 months ago by ufukuyan
  0

• Request for Alpha-CLIP with LLaVA Web Demo and Local Demo

  #11 opened a year ago by X1AOX1A
  3

• The magic number of 1.9231 and 6

  #28 opened a year ago by Wangt-CN
  2

• Annotations of the generated Imagenet

  #29 opened a year ago by callsys
  2

• AhphaCLIP with llm Demo error

  #39 opened a year ago by yjtlab
  2

• Demo error

  #38 opened a year ago by YasuoFly
  5

• What data enhancements were used in AlphaCLIP?

  #26 opened a year ago by DesertsP
  3

• can you provided the mask of Imagenet ？

  #33 opened a year ago by llf1234
  1

• Captions in GRIT

  #41 opened a year ago by jiaosiyu1999
  1

• Do you have plans to release the training code based on openclip?

  #32 opened a year ago by gongjizhang
  1

• when will release alphaclip with ViT-H/14

  #40 opened a year ago by akk-123
  1

• Could you release the code of integrating blip2 with alpha clip?

  #27 opened a year ago by Akshay1-6180
  4

• Fail to download clip_l14_grit+mim_fultune_6xe.pth

  #37 opened a year ago by donggoing
  2

• Poor performance on COCO dataset.

  #36 opened a year ago by xuanpuZhao
  0

• Table 6: Performance of Alpha-CLIP in region level captioning

  #34 opened a year ago by jetyingjia
  1

• Do you consider trying Alpha-DINOv2?

  #31 opened a year ago by grainseed
  1

• Will you provide code for the data generation process?

  #25 opened a year ago by DesertsP
  2

• Question: Can you provide some guidance for finetuning MLLM with alpha-clip vision encoder?

  #24 opened a year ago by XuRui314
  2

• Encoding Images with Alpha Channel?

  #23 opened a year ago by DavidGetter1
  6

• ViT-H/14 Model

  #22 opened a year ago by zhangh0920
  2

• for one image，regardless of how the alpha channel is modified，feature similarity is consistently above 0.97 （even between mask=0 and mask=1)

  #12 opened a year ago by llf1234
  2

• Alpha clip has reduced zero shooting ability compared to the original clip？

  #13 opened a year ago by Originlightwkp
  1

• question about the alpha-clip combined with LLaVA-7b

  #14 opened a year ago by xinli2008
  11

• AttributeError: 'NoneType' object has no attribute 'from_pretrained'

  #15 opened a year ago by justinday123
  1

• The Alpha-clip demo with LLAVA will constantly repeat a sentence under certain specific images.

  #20 opened a year ago by didiforgithub
  2