Computer scienceData scienceNLPMain NLP tasksImage recognition as an NLP task

OCR Implementation

Vision Encoder Decoder

Report a typo

In Transformers Vision Encoder Decoder models the decoder is usually...

Select one option from the list

a Vision Transformers decoder model (ImageGPT)

a language model (GPT2, BERT)

a Vision Transformers model (ImageGPT, DiT)

a language decoder model (GPT2)

___

Create a free account to access the full topic