# COCO Fine-tuning

GIT is a Transformer-based image-to-text generation model capable of generating descriptive text from input images.

GIT is a Transformer-based image-to-text generation model capable of generating descriptive text from input images.

An object detection model fine-tuned on the COCO dataset based on facebook/detr-resnet-50

An image caption generation model based on the VisionEncoderDecoder architecture, using Swin Transformer as the visual encoder and GPT-2 as the decoder, fine-tuned on the COCO2014 dataset

GIT is a Transformer-based generative image-to-text model capable of generating descriptive text from images.

GIT is a Transformer decoder-based vision-language model capable of generating image captions and performing visual question answering

GIT is a Transformer decoder based on CLIP image tokens and text tokens, used for tasks such as image caption generation and visual question answering.

A Chinese image-text retrieval model fine-tuned on the COCO-ir dataset based on the Chinese multimodal pretraining model Mengzi-Oscar