Discussions

• 7 You must be logged in to vote

  🙌

  A beginner's guide to fine-tuning the CLIP model for your downstream tasks using OpenClip

  ShuxunoO started Jan 27, 2024 in Show and tell

  

  

  

  

  4
• 2 You must be logged in to vote

  💬

  Was there a material difference in training between laion/CLIP-ViT-B-16-laion2B-s34B-b88K and laion/CLIP-ViT-B-32-laion2B-s34B-b79K?

  jn2clark started Jul 12, 2024 in General

  

  

  1
• 4 You must be logged in to vote

  🙌

  A Beginner's Guide to Fine-Tuning CLIP Models

  ellie-sleightholm started Jul 9, 2024 in Show and tell

  

  

  0
• 1 You must be logged in to vote

  🙏

  How do you profile the CLIP models

  X-funbean asked Jun 28, 2024 in Q&A · Unanswered

  

  

  1
• 1 You must be logged in to vote

  💬

  Compatible with AWS H100 p5 instances

  rizhashmi started Jun 13, 2024 in General

  

  

  1
• 1 You must be logged in to vote

  🙏

  Best practice with distributed training?

  songtianhui asked Jun 12, 2024 in Q&A · Answered

  

  

  1
• 1 You must be logged in to vote

  🙏

  Unknown model (convnext_xxlarge)

  orrzohar asked Mar 30, 2023 in Q&A · Unanswered

  

  

  

  

  7
• 1 You must be logged in to vote

  🙏

  recommended number of fine-tuning samples & batch size?

  nihirv asked Dec 28, 2023 in Q&A · Unanswered

  

  

  1
• 1 You must be logged in to vote

  🙏

  Load hybrid-clip in open_clip

  code-ishwar asked Apr 17, 2024 in Q&A · Unanswered

  

  

  1
• 1 You must be logged in to vote

  🙏

  Loading an Open_Clip Model in Nvidia Triton Server?

  cuzokwe asked Jun 4, 2024 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  Conceptual help on SigLIP + pre-trained CLIP

  miguelalba96 asked Jun 4, 2024 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  How to inference trained checkpoint on my own dataset?

  guoyanan1g asked May 18, 2024 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  Long context CLIP

  nicolas-dufour asked Apr 8, 2024 in Q&A · Unanswered

  

  

  

  

  3
• 1 You must be logged in to vote

  🙏

  Handling Negative Pairs in Fine-Tuning of CLIP Models

  doramasma asked May 8, 2024 in Q&A · Unanswered

  

  

  1
• 1 You must be logged in to vote

  🙏

  [1,512] Data conversion

  lwtgithublwt asked May 8, 2024 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  There is way to increase context length for pretrained models?

  PARSA-MHMDI asked Apr 11, 2024 in Q&A · Unanswered

  

  

  1
• 1 You must be logged in to vote

  🙏

  datasets for pretrained models

  mikelee-dev asked Apr 2, 2024 in Q&A · Unanswered

  

  

  

  

  3
• 1 You must be logged in to vote

  🙏

  How to determine the --batch_size when training from scratch?

  lishuai-97 asked Mar 28, 2024 in Q&A · Answered

  

  

  3
• 1 You must be logged in to vote

  🙏

  End-to-End Fine-tuning OpenCLIP on around 70k Image Dataset

  Researcher-DL asked Mar 7, 2024 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  openclip to Unity

  newzaungo3 asked Mar 4, 2024 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  💡

  feature request: return model size

  simonmcnair started Mar 2, 2024 in Ideas

  

  

  1
• 1 You must be logged in to vote

  🙏

  Will fine-tuning affect the ability of the original search?

  Daydaylight asked Feb 23, 2024 in Q&A · Unanswered

  

  

  1
• 1 You must be logged in to vote

  🙏

  How much GPU memory can SigLIP save compared with CLIP?

  Pluto-Jin asked Feb 22, 2024 in Q&A · Unanswered

  

  

  0
• 1 You must be logged in to vote

  🙏

  Loss isn't converging

  zhaowenZhou asked Feb 19, 2024 in Q&A · Unanswered

  

  

  1
• 1 You must be logged in to vote

  🙏

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

  githubusersel asked Jan 23, 2024 in Q&A · Unanswered

  

  

  1