search

ruotianluo / ImageCaptioning.pytorch

I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)
MIT License
1.43k stars 409 forks source link

model accurate #159

Open yemanzhongting opened 2 years ago

yemanzhongting commented 2 years ago

Hello author, I used the image caption model you provided, the accuracy is good, but the inference is slow. I saw that there is a transformer-based nlpconnect/vit-gpt2-image-captioning model that computes very fast, I would like to ask which model is more accurate? No offense, thanks.

ruotianluo commented 2 years ago

Sorry, I didn't follow this. Can you post their performance?

yemanzhongting commented 2 years ago

Sorry, I didn't follow this. Can you post their performance?

https://huggingface.co/nlpconnect/vit-gpt2-image-captioning