文章概览
CV
基础
CNN
超分
edsr
是一个基础的网络结构,2017年的,针对超分
从nlp来的
ViT
An image is worth 16x16 words: Transformers for image recognition at scale(ViT)
code: https://github.com/google-research/vision_transformergithub.com
CLIP
blog:https://openai.com/blog/clip/
paper:https://arxiv.org/pdf/2103.00020.pdf
code:https://github.com/openai/CLIP
NLP
基础
Transformer
预训练
GPT(Generative Pre-Training)
paper:https://www.cs.ubc.ca/~amuham01/LING530/papers/radford2018improving.pdf
code:https://openai.com/blog/language-unsupervised/
BERT
paper:https://arxiv.org/abs/1810.04805
code:https://github.com/google-research/[bert](https://so.csdn.net/so/search?q=bert&spm=1001.2101.3001.7020)
多想多做,发篇一作