你即將離開本站

並前往https://paperswithcode.com/paper/generative-pretraining-from-pixels

Generative Pretraining from Pixels | Papers With Code

Despite training on low-resolution ImageNet without labels, we find that a GPT-2 scale model learns strong image representations as measured by linear ...

確定！ 回上一頁

查詢 「Image GPT」的人也找了：

  1. Image GPT
    2.
  2. OpenAI
    3.
  3. OpenAI GPT
    4.
  4. GPT-2
    5.
  5. I gpt
    6.
  6. Text to image API
    7.
  7. GPT-3 model
    8.
  8. Transformer on image
    9.